feat(route): add OpenRouter discounted models route - #23106
Open
codacy20 wants to merge 1 commit into
Open
Conversation
codacy20
changed the title
Contributor
|
Successfully generated as following: http://localhost:1200/openrouter/models - Success ✔️<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
<channel>
<title>OpenRouter discounted models</title>
<link>https://openrouter.ai/models?order=discount-high-to-low</link>
<atom:link href="http://localhost:1200/openrouter/models" rel="self" type="application/rss+xml"></atom:link>
<description>OpenRouter discounted models - Powered by RSSHub</description>
<generator>RSSHub</generator>
<webMaster>contact@rsshub.app (RSSHub)</webMaster>
<language>en</language>
<lastBuildDate>Mon, 24 Aug 2026 21:18:44 GMT</lastBuildDate>
<ttl>5</ttl>
<item>
<title>Upstage: Solar Pro 4 - 90% off</title>
<description>Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive work, and coding.</description>
<link>https://openrouter.ai/upstage/solar-pro4</link>
<guid isPermaLink="false">https://openrouter.ai/upstage/solar-pro4</guid>
<category>Academia</category>
<category>Finance</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Science</category>
<category>Technology</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash (batch) - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Google Gemini Flash Latest - 75% off</title>
<description>This model always redirects to the latest model in the Google Gemini Flash family.</description>
<link>https://openrouter.ai/~google/gemini-flash-latest</link>
<guid isPermaLink="false">https://openrouter.ai/~google/gemini-flash-latest</guid>
</item>
<item>
<title>Qwen: Qwen3 235B A22B Instruct 2507 - 75% off</title>
<description>Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following, logical reasoning, math, code, and tool usage. The model supports a native 262K context length and does not implement "thinking mode" (<think> blocks).
Compared to its base variant, this version delivers significant gains in knowledge coverage, long-context reasoning, coding benchmarks, and alignment with open-ended tasks. It is particularly strong on multilingual understanding, math reasoning (e.g., AIME, HMMT), and alignment evaluations like Arena-Hard and WritingBench.</think></description>
<link>https://openrouter.ai/qwen/qwen3-235b-a22b-2507</link>
<guid isPermaLink="false">https://openrouter.ai/qwen/qwen3-235b-a22b-2507</guid>
<category>Academia</category>
<category>Roleplay</category>
<category>Translation</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Pro 0423 - 70% off</title>
<description>DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.
Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-pro</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-pro</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Ling-3.0-flash - 65% off</title>
<description>*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*.
The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers to complete more useful work within constrained token, latency, and serving-cost budgets.</description>
<link>https://openrouter.ai/inclusionai/ling-3.0-flash</link>
<guid isPermaLink="false">https://openrouter.ai/inclusionai/ling-3.0-flash</guid>
<category>Legal</category>
<category>Translation</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Flash 0423 - 61% off</title>
<description>DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.
The model includes hybrid attention for efficient long-context processing. Reasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-flash</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>ByteDance: Seedance 2.0 Mini - 60% off</title>
<description>Seedance 2.0 Mini is a video generation model from ByteDance. It supports text-to-video, image-to-video with first and last frame control, and multimodal reference-to-video with image, video, and audio inputs. It supports 480p and 720p output for 4-15 second videos. The number of tokens is given by (height of output video * width of output video * duration * 24) / 1024</description>
<link>https://openrouter.ai/bytedance/seedance-2.0-mini</link>
<guid isPermaLink="false">https://openrouter.ai/bytedance/seedance-2.0-mini</guid>
</item>
<item>
<title>Meituan: LongCat 2.0 - 60% off</title>
<description>LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic workflows.</description>
<link>https://openrouter.ai/meituan/longcat-2.0</link>
<guid isPermaLink="false">https://openrouter.ai/meituan/longcat-2.0</guid>
</item>
<item>
<title>MiniMax: MiniMax M2.7 - 60% off</title>
<description>MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments.
Trained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.</description>
<link>https://openrouter.ai/minimax/minimax-m2.7</link>
<guid isPermaLink="false">https://openrouter.ai/minimax/minimax-m2.7</guid>
<category>Marketing</category>
<category>Technology</category>
</item>
<item>
<title>Qwen: Qwen3 30B A3B Instruct 2507 - 55% off</title>
<description>Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and agentic tool use. Post-trained on instruction data, it demonstrates competitive performance across reasoning (AIME, ZebraLogic), coding (MultiPL-E, LiveCodeBench), and alignment (IFEval, WritingBench) benchmarks. It outperforms its non-instruct variant on subjective and open-ended tasks while retaining strong factual and coding performance.</description>
<link>https://openrouter.ai/qwen/qwen3-30b-a3b-instruct-2507</link>
<guid isPermaLink="false">https://openrouter.ai/qwen/qwen3-30b-a3b-instruct-2507</guid>
<category>Marketing</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol Pro (batch) - 50% off</title>
<description>GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.
Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol-pro</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol-pro</guid>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol Pro - 50% off</title>
<description>GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.
Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol-pro</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol-pro</guid>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol (batch) - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>OpenAI GPT Latest - 50% off</title>
<description>This model always redirects to the latest model in the OpenAI GPT family.</description>
<link>https://openrouter.ai/~openai/gpt-latest</link>
<guid isPermaLink="false">https://openrouter.ai/~openai/gpt-latest</guid>
</item>
<item>
<title>MoonshotAI: Kimi K2.6 - 43% off</title>
<description>Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.</description>
<link>https://openrouter.ai/moonshotai/kimi-k2.6</link>
<guid isPermaLink="false">https://openrouter.ai/moonshotai/kimi-k2.6</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Trivia</category>
</item>
<item>
<title>Poolside: Laguna XS 2.1 - 40% off</title>
<description>Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines tool calling and reasoning capabilities with a compact footprint, offering a 256K context window and up to 32K output tokens. Quantized to FP8 for fast, cost-efficient agentic coding workflows.
Laguna XS 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna XS 2.1 is subject to the [OpenMDW-1.1 License](https://openmdw.ai/license/1-1/), and should be used consistently with Poolside's [Acceptable Use Policy](https://poolside.ai/legal/acceptable-use-policy). We advise against circumventing Laguna XS 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.
Please report security vulnerabilities or safety concerns to [security@poolside.ai](mailto:security@poolside.ai).
If you are using Laguna XS 2.1 for free, we may use your inputs and outputs to train and improve our models.</description>
<link>https://openrouter.ai/poolside/laguna-xs-2.1</link>
<guid isPermaLink="false">https://openrouter.ai/poolside/laguna-xs-2.1</guid>
</item>
<item>
<title>Z.ai: GLM 5 - 40% off</title>
<description>GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.</description>
<link>https://openrouter.ai/z-ai/glm-5</link>
<guid isPermaLink="false">https://openrouter.ai/z-ai/glm-5</guid>
<category>Roleplay</category>
</item>
<item>
<title>Z.ai: GLM 5.1 - 36% off</title>
<description>GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on a single task for more than 8 hours, autonomously planning, executing, and improving itself throughout the process, ultimately delivering complete, engineering-grade results.</description>
<link>https://openrouter.ai/z-ai/glm-5.1</link>
<guid isPermaLink="false">https://openrouter.ai/z-ai/glm-5.1</guid>
<category>Roleplay</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5-Pro - 30% off</title>
<description>MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5-pro</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5-pro</guid>
<category>Finance</category>
<category>Marketing</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V3.2 - 28% off</title>
<description>DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.
Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)</description>
<link>https://openrouter.ai/deepseek/deepseek-v3.2</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v3.2</guid>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5 - 15% off</title>
<description>MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>MiniMax: MiniMax M2 - 15% off</title>
<description>MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning, tool use, and multi-step task execution while maintaining low latency and deployment efficiency.
The model excels in code generation, multi-file editing, compile-run-fix loops, and test-validated repair, showing strong results on SWE-Bench Verified, Multi-SWE-Bench, and Terminal-Bench. It also performs competitively in agentic evaluations such as BrowseComp and GAIA, effectively handling long-horizon planning, retrieval, and recovery from execution errors.
Benchmarked by [Artificial Analysis](https://artificialanalysis.ai/models/minimax-m2), MiniMax-M2 ranks among the top open-source models for composite intelligence, spanning mathematics, science, and instruction-following. Its small activation footprint enables fast inference, high concurrency, and improved unit economics, making it well-suited for large-scale agents, developer assistants, and reasoning-driven applications that require responsiveness and cost efficiency.
To avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns. Learn more about using reasoning_details to pass back reasoning in our [docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks).</description>
<link>https://openrouter.ai/minimax/minimax-m2</link>
<guid isPermaLink="false">https://openrouter.ai/minimax/minimax-m2</guid>
</item>
<item>
<title>Poolside: Laguna S 2.1 - 10% off</title>
<description>Laguna S 2.1 is the latest coding agent model from [Poolside](<https: poolside.ai="">). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and 40.4% on DeepSWE, making it one of the strongest coding models in its category. Open-weight under the OpenMDW-1.1 license.
Laguna S 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna S 2.1 is subject to the [OpenMDW-1.1 License](<https: openmdw.ai="" license="" 1-1="">), and should be used consistently with Poolside's [Acceptable Use Policy](<https: poolside.ai="" legal="" acceptable-use-policy="">). We advise against circumventing Laguna S 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.
Please report security vulnerabilities or safety concerns to [security@poolside.ai](<mailto:security@poolside.ai>).
If you are using Laguna S 2.1 for free, we may use your inputs and outputs to train and improve our models.</mailto:security@poolside.ai></https:></https:></https:></description>
<link>https://openrouter.ai/poolside/laguna-s-2.1</link>
<guid isPermaLink="false">https://openrouter.ai/poolside/laguna-s-2.1</guid>
</item>
<item>
<title>DeepSeek: DeepSeek V3 - 10% off</title>
<description>DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations reveal that the model outperforms other open-source models and rivals leading closed-source models.
For model details, please visit [the DeepSeek-V3 repo](https://github.com/deepseek-ai/DeepSeek-V3) for more information, or see the [launch announcement](https://api-docs.deepseek.com/news/news1226).</description>
<link>https://openrouter.ai/deepseek/deepseek-chat</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-chat</guid>
</item>
<item>
<title>Tencent: Hy3 - 5% off</title>
<description>Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.
Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.</description>
<link>https://openrouter.ai/tencent/hy3</link>
<guid isPermaLink="false">https://openrouter.ai/tencent/hy3</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Poolside: Laguna S 2.1 (free) - 10% off</title>
<description>Laguna S 2.1 is the latest coding agent model from [Poolside](<https: poolside.ai="">). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and 40.4% on DeepSWE, making it one of the strongest coding models in its category. Open-weight under the OpenMDW-1.1 license.
Laguna S 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna S 2.1 is subject to the [OpenMDW-1.1 License](<https: openmdw.ai="" license="" 1-1="">), and should be used consistently with Poolside's [Acceptable Use Policy](<https: poolside.ai="" legal="" acceptable-use-policy="">). We advise against circumventing Laguna S 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.
Please report security vulnerabilities or safety concerns to [security@poolside.ai](<mailto:security@poolside.ai>).
If you are using Laguna S 2.1 for free, we may use your inputs and outputs to train and improve our models.</mailto:security@poolside.ai></https:></https:></https:></description>
<link>https://openrouter.ai/poolside/laguna-s-2.1</link>
<guid isPermaLink="false">https://openrouter.ai/poolside/laguna-s-2.1</guid>
</item>
<item>
<title>Poolside: Laguna XS 2.1 (free) - 40% off</title>
<description>Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines tool calling and reasoning capabilities with a compact footprint, offering a 256K context window and up to 32K output tokens. Quantized to FP8 for fast, cost-efficient agentic coding workflows.
Laguna XS 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna XS 2.1 is subject to the [OpenMDW-1.1 License](https://openmdw.ai/license/1-1/), and should be used consistently with Poolside's [Acceptable Use Policy](https://poolside.ai/legal/acceptable-use-policy). We advise against circumventing Laguna XS 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.
Please report security vulnerabilities or safety concerns to [security@poolside.ai](mailto:security@poolside.ai).
If you are using Laguna XS 2.1 for free, we may use your inputs and outputs to train and improve our models.</description>
<link>https://openrouter.ai/poolside/laguna-xs-2.1</link>
<guid isPermaLink="false">https://openrouter.ai/poolside/laguna-xs-2.1</guid>
</item>
</channel>
</rss>http://localhost:1200/openrouter/models/programming - Success ✔️<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
<channel>
<title>OpenRouter Programming discounted models</title>
<link>https://openrouter.ai/models?order=discount-high-to-low</link>
<atom:link href="http://localhost:1200/openrouter/models/programming" rel="self" type="application/rss+xml"></atom:link>
<description>OpenRouter Programming discounted models - Powered by RSSHub</description>
<generator>RSSHub</generator>
<webMaster>contact@rsshub.app (RSSHub)</webMaster>
<language>en</language>
<lastBuildDate>Mon, 24 Aug 2026 21:18:44 GMT</lastBuildDate>
<ttl>5</ttl>
<item>
<title>Upstage: Solar Pro 4 - 90% off</title>
<description>Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive work, and coding.</description>
<link>https://openrouter.ai/upstage/solar-pro4</link>
<guid isPermaLink="false">https://openrouter.ai/upstage/solar-pro4</guid>
<category>Academia</category>
<category>Finance</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Science</category>
<category>Technology</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash (batch) - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Pro 0423 - 70% off</title>
<description>DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.
Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-pro</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-pro</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Flash 0423 - 61% off</title>
<description>DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.
The model includes hybrid attention for efficient long-context processing. Reasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-flash</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol (batch) - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>MoonshotAI: Kimi K2.6 - 43% off</title>
<description>Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.</description>
<link>https://openrouter.ai/moonshotai/kimi-k2.6</link>
<guid isPermaLink="false">https://openrouter.ai/moonshotai/kimi-k2.6</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Trivia</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5-Pro - 30% off</title>
<description>MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5-pro</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5-pro</guid>
<category>Finance</category>
<category>Marketing</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Trivia</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5 - 15% off</title>
<description>MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Tencent: Hy3 - 5% off</title>
<description>Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.
Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.</description>
<link>https://openrouter.ai/tencent/hy3</link>
<guid isPermaLink="false">https://openrouter.ai/tencent/hy3</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
</channel>
</rss>http://localhost:1200/openrouter/models/finance - Success ✔️<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
<channel>
<title>OpenRouter Finance discounted models</title>
<link>https://openrouter.ai/models?order=discount-high-to-low</link>
<atom:link href="http://localhost:1200/openrouter/models/finance" rel="self" type="application/rss+xml"></atom:link>
<description>OpenRouter Finance discounted models - Powered by RSSHub</description>
<generator>RSSHub</generator>
<webMaster>contact@rsshub.app (RSSHub)</webMaster>
<language>en</language>
<lastBuildDate>Mon, 24 Aug 2026 21:18:44 GMT</lastBuildDate>
<ttl>5</ttl>
<item>
<title>Upstage: Solar Pro 4 - 90% off</title>
<description>Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive work, and coding.</description>
<link>https://openrouter.ai/upstage/solar-pro4</link>
<guid isPermaLink="false">https://openrouter.ai/upstage/solar-pro4</guid>
<category>Academia</category>
<category>Finance</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Science</category>
<category>Technology</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash (batch) - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Pro 0423 - 70% off</title>
<description>DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.
Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-pro</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-pro</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Flash 0423 - 61% off</title>
<description>DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.
The model includes hybrid attention for efficient long-context processing. Reasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-flash</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol (batch) - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>MoonshotAI: Kimi K2.6 - 43% off</title>
<description>Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.</description>
<link>https://openrouter.ai/moonshotai/kimi-k2.6</link>
<guid isPermaLink="false">https://openrouter.ai/moonshotai/kimi-k2.6</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Trivia</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5-Pro - 30% off</title>
<description>MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5-pro</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5-pro</guid>
<category>Finance</category>
<category>Marketing</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V3.2 - 28% off</title>
<description>DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.
Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)</description>
<link>https://openrouter.ai/deepseek/deepseek-v3.2</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v3.2</guid>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5 - 15% off</title>
<description>MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Tencent: Hy3 - 5% off</title>
<description>Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.
Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.</description>
<link>https://openrouter.ai/tencent/hy3</link>
<guid isPermaLink="false">https://openrouter.ai/tencent/hy3</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
</channel>
</rss>... |
github-actions
Bot
added
the
auto: ready to review
Contributor
http://localhost:1200/openrouter/models/legal - Success ✔️<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
<channel>
<title>OpenRouter Legal discounted models</title>
<link>https://openrouter.ai/models?order=discount-high-to-low</link>
<atom:link href="http://localhost:1200/openrouter/models/legal" rel="self" type="application/rss+xml"></atom:link>
<description>OpenRouter Legal discounted models - Powered by RSSHub</description>
<generator>RSSHub</generator>
<webMaster>contact@rsshub.app (RSSHub)</webMaster>
<language>en</language>
<lastBuildDate>Mon, 24 Aug 2026 21:18:44 GMT</lastBuildDate>
<ttl>5</ttl>
<item>
<title>Google: Gemini 3.7 Flash (batch) - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Pro 0423 - 70% off</title>
<description>DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.
Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-pro</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-pro</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Ling-3.0-flash - 65% off</title>
<description>*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*.
The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers to complete more useful work within constrained token, latency, and serving-cost budgets.</description>
<link>https://openrouter.ai/inclusionai/ling-3.0-flash</link>
<guid isPermaLink="false">https://openrouter.ai/inclusionai/ling-3.0-flash</guid>
<category>Legal</category>
<category>Translation</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Flash 0423 - 61% off</title>
<description>DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.
The model includes hybrid attention for efficient long-context processing. Reasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-flash</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol (batch) - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>DeepSeek: DeepSeek V3.2 - 28% off</title>
<description>DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.
Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)</description>
<link>https://openrouter.ai/deepseek/deepseek-v3.2</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v3.2</guid>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5 - 15% off</title>
<description>MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Tencent: Hy3 - 5% off</title>
<description>Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.
Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.</description>
<link>https://openrouter.ai/tencent/hy3</link>
<guid isPermaLink="false">https://openrouter.ai/tencent/hy3</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
</channel>
</rss>http://localhost:1200/openrouter/models/health - Success ✔️<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
<channel>
<title>OpenRouter Health discounted models</title>
<link>https://openrouter.ai/models?order=discount-high-to-low</link>
<atom:link href="http://localhost:1200/openrouter/models/health" rel="self" type="application/rss+xml"></atom:link>
<description>OpenRouter Health discounted models - Powered by RSSHub</description>
<generator>RSSHub</generator>
<webMaster>contact@rsshub.app (RSSHub)</webMaster>
<language>en</language>
<lastBuildDate>Mon, 24 Aug 2026 21:18:44 GMT</lastBuildDate>
<ttl>5</ttl>
<item>
<title>Google: Gemini 3.7 Flash (batch) - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Pro 0423 - 70% off</title>
<description>DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.
Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-pro</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-pro</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Flash 0423 - 61% off</title>
<description>DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.
The model includes hybrid attention for efficient long-context processing. Reasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-flash</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol (batch) - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>MoonshotAI: Kimi K2.6 - 43% off</title>
<description>Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.</description>
<link>https://openrouter.ai/moonshotai/kimi-k2.6</link>
<guid isPermaLink="false">https://openrouter.ai/moonshotai/kimi-k2.6</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V3.2 - 28% off</title>
<description>DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.
Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)</description>
<link>https://openrouter.ai/deepseek/deepseek-v3.2</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v3.2</guid>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5 - 15% off</title>
<description>MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Tencent: Hy3 - 5% off</title>
<description>Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.
Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.</description>
<link>https://openrouter.ai/tencent/hy3</link>
<guid isPermaLink="false">https://openrouter.ai/tencent/hy3</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
</channel>
</rss>http://localhost:1200/openrouter/models/marketing - Success ✔️<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
<channel>
<title>OpenRouter Marketing discounted models</title>
<link>https://openrouter.ai/models?order=discount-high-to-low</link>
<atom:link href="http://localhost:1200/openrouter/models/marketing" rel="self" type="application/rss+xml"></atom:link>
<description>OpenRouter Marketing discounted models - Powered by RSSHub</description>
<generator>RSSHub</generator>
<webMaster>contact@rsshub.app (RSSHub)</webMaster>
<language>en</language>
<lastBuildDate>Mon, 24 Aug 2026 21:18:44 GMT</lastBuildDate>
<ttl>5</ttl>
<item>
<title>Upstage: Solar Pro 4 - 90% off</title>
<description>Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive work, and coding.</description>
<link>https://openrouter.ai/upstage/solar-pro4</link>
<guid isPermaLink="false">https://openrouter.ai/upstage/solar-pro4</guid>
<category>Academia</category>
<category>Finance</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Science</category>
<category>Technology</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash (batch) - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Pro 0423 - 70% off</title>
<description>DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.
Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-pro</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-pro</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Flash 0423 - 61% off</title>
<description>DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.
The model includes hybrid attention for efficient long-context processing. Reasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-flash</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>MiniMax: MiniMax M2.7 - 60% off</title>
<description>MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments.
Trained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.</description>
<link>https://openrouter.ai/minimax/minimax-m2.7</link>
<guid isPermaLink="false">https://openrouter.ai/minimax/minimax-m2.7</guid>
<category>Marketing</category>
<category>Technology</category>
</item>
<item>
<title>Qwen: Qwen3 30B A3B Instruct 2507 - 55% off</title>
<description>Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and agentic tool use. Post-trained on instruction data, it demonstrates competitive performance across reasoning (AIME, ZebraLogic), coding (MultiPL-E, LiveCodeBench), and alignment (IFEval, WritingBench) benchmarks. It outperforms its non-instruct variant on subjective and open-ended tasks while retaining strong factual and coding performance.</description>
<link>https://openrouter.ai/qwen/qwen3-30b-a3b-instruct-2507</link>
<guid isPermaLink="false">https://openrouter.ai/qwen/qwen3-30b-a3b-instruct-2507</guid>
<category>Marketing</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol (batch) - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5-Pro - 30% off</title>
<description>MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5-pro</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5-pro</guid>
<category>Finance</category>
<category>Marketing</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V3.2 - 28% off</title>
<description>DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.
Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)</description>
<link>https://openrouter.ai/deepseek/deepseek-v3.2</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v3.2</guid>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5 - 15% off</title>
<description>MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Tencent: Hy3 - 5% off</title>
<description>Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.
Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.</description>
<link>https://openrouter.ai/tencent/hy3</link>
<guid isPermaLink="false">https://openrouter.ai/tencent/hy3</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
</channel>
</rss>http://localhost:1200/openrouter/models/seo - Success ✔️<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
<channel>
<title>OpenRouter SEO discounted models</title>
<link>https://openrouter.ai/models?order=discount-high-to-low</link>
<atom:link href="http://localhost:1200/openrouter/models/seo" rel="self" type="application/rss+xml"></atom:link>
<description>OpenRouter SEO discounted models - Powered by RSSHub</description>
<generator>RSSHub</generator>
<webMaster>contact@rsshub.app (RSSHub)</webMaster>
<language>en</language>
<lastBuildDate>Mon, 24 Aug 2026 21:18:44 GMT</lastBuildDate>
<ttl>5</ttl>
<item>
<title>Upstage: Solar Pro 4 - 90% off</title>
<description>Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive work, and coding.</description>
<link>https://openrouter.ai/upstage/solar-pro4</link>
<guid isPermaLink="false">https://openrouter.ai/upstage/solar-pro4</guid>
<category>Academia</category>
<category>Finance</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Science</category>
<category>Technology</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash (batch) - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Pro 0423 - 70% off</title>
<description>DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.
Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-pro</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-pro</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Flash 0423 - 61% off</title>
<description>DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.
The model includes hybrid attention for efficient long-context processing. Reasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-flash</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol (batch) - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>MoonshotAI: Kimi K2.6 - 43% off</title>
<description>Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.</description>
<link>https://openrouter.ai/moonshotai/kimi-k2.6</link>
<guid isPermaLink="false">https://openrouter.ai/moonshotai/kimi-k2.6</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V3.2 - 28% off</title>
<description>DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.
Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)</description>
<link>https://openrouter.ai/deepseek/deepseek-v3.2</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v3.2</guid>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5 - 15% off</title>
<description>MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Tencent: Hy3 - 5% off</title>
<description>Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.
Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.</description>
<link>https://openrouter.ai/tencent/hy3</link>
<guid isPermaLink="false">https://openrouter.ai/tencent/hy3</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
</channel>
</rss>http://localhost:1200/openrouter/models/academia - Success ✔️<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
<channel>
<title>OpenRouter Academia discounted models</title>
<link>https://openrouter.ai/models?order=discount-high-to-low</link>
<atom:link href="http://localhost:1200/openrouter/models/academia" rel="self" type="application/rss+xml"></atom:link>
<description>OpenRouter Academia discounted models - Powered by RSSHub</description>
<generator>RSSHub</generator>
<webMaster>contact@rsshub.app (RSSHub)</webMaster>
<language>en</language>
<lastBuildDate>Mon, 24 Aug 2026 21:18:44 GMT</lastBuildDate>
<ttl>5</ttl>
<item>
<title>Upstage: Solar Pro 4 - 90% off</title>
<description>Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive work, and coding.</description>
<link>https://openrouter.ai/upstage/solar-pro4</link>
<guid isPermaLink="false">https://openrouter.ai/upstage/solar-pro4</guid>
<category>Academia</category>
<category>Finance</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Science</category>
<category>Technology</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash (batch) - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Qwen: Qwen3 235B A22B Instruct 2507 - 75% off</title>
<description>Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following, logical reasoning, math, code, and tool usage. The model supports a native 262K context length and does not implement "thinking mode" (<think> blocks).
Compared to its base variant, this version delivers significant gains in knowledge coverage, long-context reasoning, coding benchmarks, and alignment with open-ended tasks. It is particularly strong on multilingual understanding, math reasoning (e.g., AIME, HMMT), and alignment evaluations like Arena-Hard and WritingBench.</think></description>
<link>https://openrouter.ai/qwen/qwen3-235b-a22b-2507</link>
<guid isPermaLink="false">https://openrouter.ai/qwen/qwen3-235b-a22b-2507</guid>
<category>Academia</category>
<category>Roleplay</category>
<category>Translation</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Pro 0423 - 70% off</title>
<description>DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.
Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-pro</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-pro</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Flash 0423 - 61% off</title>
<description>DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.
The model includes hybrid attention for efficient long-context processing. Reasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-flash</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol (batch) - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>MoonshotAI: Kimi K2.6 - 43% off</title>
<description>Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.</description>
<link>https://openrouter.ai/moonshotai/kimi-k2.6</link>
<guid isPermaLink="false">https://openrouter.ai/moonshotai/kimi-k2.6</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Trivia</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5 - 15% off</title>
<description>MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Tencent: Hy3 - 5% off</title>
<description>Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.
Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.</description>
<link>https://openrouter.ai/tencent/hy3</link>
<guid isPermaLink="false">https://openrouter.ai/tencent/hy3</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
</channel>
</rss>... |
Contributor
http://localhost:1200/openrouter/models/science - Success ✔️<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
<channel>
<title>OpenRouter Science discounted models</title>
<link>https://openrouter.ai/models?order=discount-high-to-low</link>
<atom:link href="http://localhost:1200/openrouter/models/science" rel="self" type="application/rss+xml"></atom:link>
<description>OpenRouter Science discounted models - Powered by RSSHub</description>
<generator>RSSHub</generator>
<webMaster>contact@rsshub.app (RSSHub)</webMaster>
<language>en</language>
<lastBuildDate>Mon, 24 Aug 2026 21:18:44 GMT</lastBuildDate>
<ttl>5</ttl>
<item>
<title>Upstage: Solar Pro 4 - 90% off</title>
<description>Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive work, and coding.</description>
<link>https://openrouter.ai/upstage/solar-pro4</link>
<guid isPermaLink="false">https://openrouter.ai/upstage/solar-pro4</guid>
<category>Academia</category>
<category>Finance</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Science</category>
<category>Technology</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash (batch) - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Pro 0423 - 70% off</title>
<description>DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.
Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-pro</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-pro</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Flash 0423 - 61% off</title>
<description>DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.
The model includes hybrid attention for efficient long-context processing. Reasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-flash</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol (batch) - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>MoonshotAI: Kimi K2.6 - 43% off</title>
<description>Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.</description>
<link>https://openrouter.ai/moonshotai/kimi-k2.6</link>
<guid isPermaLink="false">https://openrouter.ai/moonshotai/kimi-k2.6</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Trivia</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5-Pro - 30% off</title>
<description>MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5-pro</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5-pro</guid>
<category>Finance</category>
<category>Marketing</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V3.2 - 28% off</title>
<description>DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.
Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)</description>
<link>https://openrouter.ai/deepseek/deepseek-v3.2</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v3.2</guid>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5 - 15% off</title>
<description>MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Tencent: Hy3 - 5% off</title>
<description>Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.
Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.</description>
<link>https://openrouter.ai/tencent/hy3</link>
<guid isPermaLink="false">https://openrouter.ai/tencent/hy3</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
</channel>
</rss>http://localhost:1200/openrouter/models/technology - Success ✔️<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
<channel>
<title>OpenRouter Technology discounted models</title>
<link>https://openrouter.ai/models?order=discount-high-to-low</link>
<atom:link href="http://localhost:1200/openrouter/models/technology" rel="self" type="application/rss+xml"></atom:link>
<description>OpenRouter Technology discounted models - Powered by RSSHub</description>
<generator>RSSHub</generator>
<webMaster>contact@rsshub.app (RSSHub)</webMaster>
<language>en</language>
<lastBuildDate>Mon, 24 Aug 2026 21:18:44 GMT</lastBuildDate>
<ttl>5</ttl>
<item>
<title>Upstage: Solar Pro 4 - 90% off</title>
<description>Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive work, and coding.</description>
<link>https://openrouter.ai/upstage/solar-pro4</link>
<guid isPermaLink="false">https://openrouter.ai/upstage/solar-pro4</guid>
<category>Academia</category>
<category>Finance</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Science</category>
<category>Technology</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash (batch) - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Pro 0423 - 70% off</title>
<description>DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.
Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-pro</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-pro</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Flash 0423 - 61% off</title>
<description>DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.
The model includes hybrid attention for efficient long-context processing. Reasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-flash</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>MiniMax: MiniMax M2.7 - 60% off</title>
<description>MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments.
Trained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.</description>
<link>https://openrouter.ai/minimax/minimax-m2.7</link>
<guid isPermaLink="false">https://openrouter.ai/minimax/minimax-m2.7</guid>
<category>Marketing</category>
<category>Technology</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol (batch) - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5-Pro - 30% off</title>
<description>MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5-pro</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5-pro</guid>
<category>Finance</category>
<category>Marketing</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V3.2 - 28% off</title>
<description>DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.
Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)</description>
<link>https://openrouter.ai/deepseek/deepseek-v3.2</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v3.2</guid>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5 - 15% off</title>
<description>MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Tencent: Hy3 - 5% off</title>
<description>Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.
Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.</description>
<link>https://openrouter.ai/tencent/hy3</link>
<guid isPermaLink="false">https://openrouter.ai/tencent/hy3</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
</channel>
</rss>http://localhost:1200/openrouter/models/translation - Success ✔️<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
<channel>
<title>OpenRouter Translation discounted models</title>
<link>https://openrouter.ai/models?order=discount-high-to-low</link>
<atom:link href="http://localhost:1200/openrouter/models/translation" rel="self" type="application/rss+xml"></atom:link>
<description>OpenRouter Translation discounted models - Powered by RSSHub</description>
<generator>RSSHub</generator>
<webMaster>contact@rsshub.app (RSSHub)</webMaster>
<language>en</language>
<lastBuildDate>Mon, 24 Aug 2026 21:18:44 GMT</lastBuildDate>
<ttl>5</ttl>
<item>
<title>Google: Gemini 3.7 Flash (batch) - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Qwen: Qwen3 235B A22B Instruct 2507 - 75% off</title>
<description>Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following, logical reasoning, math, code, and tool usage. The model supports a native 262K context length and does not implement "thinking mode" (<think> blocks).
Compared to its base variant, this version delivers significant gains in knowledge coverage, long-context reasoning, coding benchmarks, and alignment with open-ended tasks. It is particularly strong on multilingual understanding, math reasoning (e.g., AIME, HMMT), and alignment evaluations like Arena-Hard and WritingBench.</think></description>
<link>https://openrouter.ai/qwen/qwen3-235b-a22b-2507</link>
<guid isPermaLink="false">https://openrouter.ai/qwen/qwen3-235b-a22b-2507</guid>
<category>Academia</category>
<category>Roleplay</category>
<category>Translation</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Pro 0423 - 70% off</title>
<description>DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.
Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-pro</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-pro</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Ling-3.0-flash - 65% off</title>
<description>*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*.
The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers to complete more useful work within constrained token, latency, and serving-cost budgets.</description>
<link>https://openrouter.ai/inclusionai/ling-3.0-flash</link>
<guid isPermaLink="false">https://openrouter.ai/inclusionai/ling-3.0-flash</guid>
<category>Legal</category>
<category>Translation</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Flash 0423 - 61% off</title>
<description>DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.
The model includes hybrid attention for efficient long-context processing. Reasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-flash</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V3.2 - 28% off</title>
<description>DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.
Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)</description>
<link>https://openrouter.ai/deepseek/deepseek-v3.2</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v3.2</guid>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5 - 15% off</title>
<description>MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Tencent: Hy3 - 5% off</title>
<description>Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.
Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.</description>
<link>https://openrouter.ai/tencent/hy3</link>
<guid isPermaLink="false">https://openrouter.ai/tencent/hy3</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
</channel>
</rss>http://localhost:1200/openrouter/models/roleplay - Success ✔️<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
<channel>
<title>OpenRouter Roleplay discounted models</title>
<link>https://openrouter.ai/models?order=discount-high-to-low</link>
<atom:link href="http://localhost:1200/openrouter/models/roleplay" rel="self" type="application/rss+xml"></atom:link>
<description>OpenRouter Roleplay discounted models - Powered by RSSHub</description>
<generator>RSSHub</generator>
<webMaster>contact@rsshub.app (RSSHub)</webMaster>
<language>en</language>
<lastBuildDate>Mon, 24 Aug 2026 21:18:44 GMT</lastBuildDate>
<ttl>5</ttl>
<item>
<title>Google: Gemini 3.7 Flash (batch) - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Qwen: Qwen3 235B A22B Instruct 2507 - 75% off</title>
<description>Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following, logical reasoning, math, code, and tool usage. The model supports a native 262K context length and does not implement "thinking mode" (<think> blocks).
Compared to its base variant, this version delivers significant gains in knowledge coverage, long-context reasoning, coding benchmarks, and alignment with open-ended tasks. It is particularly strong on multilingual understanding, math reasoning (e.g., AIME, HMMT), and alignment evaluations like Arena-Hard and WritingBench.</think></description>
<link>https://openrouter.ai/qwen/qwen3-235b-a22b-2507</link>
<guid isPermaLink="false">https://openrouter.ai/qwen/qwen3-235b-a22b-2507</guid>
<category>Academia</category>
<category>Roleplay</category>
<category>Translation</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Pro 0423 - 70% off</title>
<description>DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.
Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-pro</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-pro</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Flash 0423 - 61% off</title>
<description>DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.
The model includes hybrid attention for efficient long-context processing. Reasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-flash</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol (batch) - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>OpenAI: GPT-5.6 Sol - 50% off</title>
<description>GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.</description>
<link>https://openrouter.ai/openai/gpt-5.6-sol</link>
<guid isPermaLink="false">https://openrouter.ai/openai/gpt-5.6-sol</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
</item>
<item>
<title>MoonshotAI: Kimi K2.6 - 43% off</title>
<description>Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.</description>
<link>https://openrouter.ai/moonshotai/kimi-k2.6</link>
<guid isPermaLink="false">https://openrouter.ai/moonshotai/kimi-k2.6</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Trivia</category>
</item>
<item>
<title>Z.ai: GLM 5 - 40% off</title>
<description>GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.</description>
<link>https://openrouter.ai/z-ai/glm-5</link>
<guid isPermaLink="false">https://openrouter.ai/z-ai/glm-5</guid>
<category>Roleplay</category>
</item>
<item>
<title>Z.ai: GLM 5.1 - 36% off</title>
<description>GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on a single task for more than 8 hours, autonomously planning, executing, and improving itself throughout the process, ultimately delivering complete, engineering-grade results.</description>
<link>https://openrouter.ai/z-ai/glm-5.1</link>
<guid isPermaLink="false">https://openrouter.ai/z-ai/glm-5.1</guid>
<category>Roleplay</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5-Pro - 30% off</title>
<description>MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5-pro</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5-pro</guid>
<category>Finance</category>
<category>Marketing</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V3.2 - 28% off</title>
<description>DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.
Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)</description>
<link>https://openrouter.ai/deepseek/deepseek-v3.2</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v3.2</guid>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5 - 15% off</title>
<description>MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Tencent: Hy3 - 5% off</title>
<description>Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.
Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.</description>
<link>https://openrouter.ai/tencent/hy3</link>
<guid isPermaLink="false">https://openrouter.ai/tencent/hy3</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
</channel>
</rss>... |
Contributor
http://localhost:1200/openrouter/models/trivia - Success ✔️<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
<channel>
<title>OpenRouter Trivia discounted models</title>
<link>https://openrouter.ai/models?order=discount-high-to-low</link>
<atom:link href="http://localhost:1200/openrouter/models/trivia" rel="self" type="application/rss+xml"></atom:link>
<description>OpenRouter Trivia discounted models - Powered by RSSHub</description>
<generator>RSSHub</generator>
<webMaster>contact@rsshub.app (RSSHub)</webMaster>
<language>en</language>
<lastBuildDate>Mon, 24 Aug 2026 21:18:44 GMT</lastBuildDate>
<ttl>5</ttl>
<item>
<title>Upstage: Solar Pro 4 - 90% off</title>
<description>Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive work, and coding.</description>
<link>https://openrouter.ai/upstage/solar-pro4</link>
<guid isPermaLink="false">https://openrouter.ai/upstage/solar-pro4</guid>
<category>Academia</category>
<category>Finance</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Science</category>
<category>Technology</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash (batch) - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Google: Gemini 3.7 Flash - 75% off</title>
<description>Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.</description>
<link>https://openrouter.ai/google/gemini-3.7-flash</link>
<guid isPermaLink="false">https://openrouter.ai/google/gemini-3.7-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Pro 0423 - 70% off</title>
<description>DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.
Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-pro</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-pro</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V4 Flash 0423 - 61% off</title>
<description>DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.
The model includes hybrid attention for efficient long-context processing. Reasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.</description>
<link>https://openrouter.ai/deepseek/deepseek-v4-flash</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v4-flash</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>MoonshotAI: Kimi K2.6 - 43% off</title>
<description>Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.</description>
<link>https://openrouter.ai/moonshotai/kimi-k2.6</link>
<guid isPermaLink="false">https://openrouter.ai/moonshotai/kimi-k2.6</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Trivia</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5-Pro - 30% off</title>
<description>MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5-pro</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5-pro</guid>
<category>Finance</category>
<category>Marketing</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Trivia</category>
</item>
<item>
<title>DeepSeek: DeepSeek V3.2 - 28% off</title>
<description>DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.
Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)</description>
<link>https://openrouter.ai/deepseek/deepseek-v3.2</link>
<guid isPermaLink="false">https://openrouter.ai/deepseek/deepseek-v3.2</guid>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Xiaomi: MiMo-V2.5 - 15% off</title>
<description>MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.</description>
<link>https://openrouter.ai/xiaomi/mimo-v2.5</link>
<guid isPermaLink="false">https://openrouter.ai/xiaomi/mimo-v2.5</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
<item>
<title>Tencent: Hy3 - 5% off</title>
<description>Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.
Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.</description>
<link>https://openrouter.ai/tencent/hy3</link>
<guid isPermaLink="false">https://openrouter.ai/tencent/hy3</guid>
<category>Academia</category>
<category>Finance</category>
<category>Health</category>
<category>Legal</category>
<category>Marketing</category>
<category>SEO</category>
<category>Programming</category>
<category>Roleplay</category>
<category>Science</category>
<category>Technology</category>
<category>Translation</category>
<category>Trivia</category>
</item>
</channel>
</rss> |
Contributor
Auto Review
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Involved Issue / 该 PR 相关 Issue
Close #
Example for the Proposed Route(s) / 路由地址示例
New RSS Route Checklist / 新 RSS 路由检查表
PuppeteerNote / 说明
Add route for discounted models on OpenRouter (
https://openrouter.ai/models?order=discount-high-to-low)./openrouter/models/programming,/openrouter/models/finance,/openrouter/models/seo, etc.) preserving discount priority with category ranking as secondary sort./api/frontend/v1/models/findand/api/frontend/v1/catalog/models) to retrieve accurate discount percentages, pricing details, and category rankings without browser automation overhead.