feat: add MiniMax as a supported LLM provider with M2.7 models by octo-patch · Pull Request #5666 · comet-ml/opik

octo-patch · 2026-03-15T12:07:32Z

Summary

Add MiniMax as a supported LLM provider for Opik, with the latest M2.7 flagship model as default.

Changes

Add MiniMax temperature clamping filter in LiteLLM util (temperature > 0 requirement)
Add MiniMax-M2.7 and MiniMax-M2.7-highspeed as new models (set M2.7 as default)
Add MiniMax-M2.5 and M2.5-highspeed as alternative models
Add model entries to frontend (providers.ts, useLLMProviderModelsData.ts) and backend (OpenRouterModelName.java)
Add model pricing data for M2.7 models in model_prices_and_context_window.json
Add comprehensive MiniMax integration documentation (minimax.mdx) with OpenAI SDK and LiteLLM examples
Add MiniMax to integrations overview and navigation
Update README with MiniMax integration link
Add unit tests for temperature clamping behavior

Why

MiniMax-M2.7 is the latest flagship model with enhanced reasoning and coding capabilities, offering a 1M token context window.

Testing

All 14 unit tests pass including MiniMax temperature clamping tests
Integration tested with MiniMax API

Add MiniMax integration documentation, temperature constraint handling, and tests to support MiniMax models (MiniMax-M2.5, MiniMax-M2.5-highspeed) as a first-class provider in Opik. Changes: - Add MiniMax integration documentation page (minimax.mdx) with usage examples for OpenAI SDK, LiteLLM, and evaluation metrics - Add MiniMax to the Model Providers section in overview and README - Add MiniMax navigation entry and redirect in docs.yml - Add MiniMax-specific temperature filter in util.py (MiniMax requires temperature > 0, so zero values are clamped to 0.01) - Add unit tests for MiniMax temperature constraint handling

baz-reviewer · 2026-03-15T12:11:47Z

apps/opik-documentation/documentation/fern/docs/tracing/integrations/minimax.mdx

+## Important Notes
+
+- **Temperature**: MiniMax models require temperature to be strictly greater than 0. If you set `temperature=0`, it will be automatically adjusted when using LiteLLM with Opik.
+- **API Compatibility**: MiniMax's API is fully compatible with the OpenAI SDK, so any OpenAI-compatible tool or framework will work with MiniMax.
+


Docs claim MiniMax temperature=0 is auto-adjusted when using LiteLLM with Opik, but the clamp is only applied in LiteLLMChatModel (sdks/python/src/opik/evaluation/models/litellm/util.py) and the Opik monitoring path (sdks/python/src/opik/evaluation/models/litellm/opik_monitor.py lines 20–94) never calls _apply_minimax_filters. Calling litellm.completion with temperature=0 and only Opik callbacks still sends temperature=0 to MiniMax and fails; can we either narrow the doc note to the evaluation-model use case or add the clamp to the LiteLLM monitoring integration?

_{Finding type: Logical Bugs | Severity: 🔴 High}

Want Baz to fix this for you? Activate Fixer

Other fix methods

Prompt for AI Agents:

In apps/opik-documentation/documentation/fern/docs/tracing/integrations/minimax.mdx around lines 208-212, the note incorrectly states that MiniMax temperature=0 is automatically adjusted when using LiteLLM with Opik. Change the wording to accurately reflect the current behavior: state that the automatic clamp only occurs when using the LiteLLMChatModel evaluation integration, not when using the generic OpikLogger callbacks; alternatively, implement the clamp in the LiteLLM monitoring integration (sdks/python/src/opik/evaluation/models/litellm/opik_monitor.py) so OpikLogger also applies _apply_minimax_filters before sending requests. Make the doc update concise and unambiguous, or if you implement the code change, add a brief comment in opik_monitor.py indicating why the clamp is needed for MiniMax compatibility.

baz-reviewer · 2026-03-15T12:11:47Z

sdks/python/src/opik/evaluation/models/litellm/util.py

+def _apply_minimax_filters(
+    params: Dict[str, Any],
+    already_warned: Set[str],
+    warn: Callable[[str, Any], None],
+) -> None:
+    """Apply MiniMax specific parameter filters.
+
+    MiniMax requires temperature to be strictly greater than 0.
+    A temperature of 0 is rejected by the API, so we clamp it to a small
+    positive value to avoid errors.
+    """
+


params['temperature'] is treated as optional, but _apply_minimax_filters only clamps values that parse to float and are <= 0.0; float(value) raises for None/non-numeric inputs, so params['temperature'] remains None. This lets MiniMax requests send a nullish temperature and the API rejects them. Can we normalize invalid/null temperatures before returning (e.g., set to 0.01 or drop/log them) so callers can rely on a positive number?

_{Finding type: Validate nullable inputs | Severity: 🔴 High}

Want Baz to fix this for you? Activate Fixer

Other fix methods

Prompt for AI Agents:

In sdks/python/src/opik/evaluation/models/litellm/util.py around lines 109-128, the _apply_minimax_filters function currently only clamps numeric temperatures <= 0 but leaves None or non-numeric values unchanged. Change the logic so that if params contains "temperature" but parsing to float fails or the parsed value is None, set params["temperature"] = 0.01 (the same clamp used for non-positive numbers) and call warn(...) to indicate an invalid/null temperature was replaced; also keep the existing behavior of clamping numeric <= 0 to 0.01. This ensures downstream callers never receive a null/invalid temperature.

- Add MiniMax-M2.7 and MiniMax-M2.7-highspeed to model lists (frontend, backend, OpenRouter enum, pricing JSON) - Update default model references from M2.5 to M2.7 in docs and tests - Add M2.7 pricing data (cache_read updated to $0.06/M tokens) - Keep all previous models as available alternatives

baz-reviewer · 2026-03-18T18:51:48Z

apps/opik-documentation/documentation/fern/docs/tracing/integrations/minimax.mdx

+from opik.evaluation.models import LiteLLMChatModel
+
+# Create a MiniMax model for evaluation
+minimax_model = LiteLLMChatModel(model_name="minimax/MiniMax-M2.7")


Should we replace the hand‑pasted minimax_model example with the generated example link or expand it to include the checklist-required intent line, a minimal runnable context with an inline behavior comment, and a maintenance note linking to the canonical/generated example and owner?

_{Finding type: Keep docs accurate | Severity: 🟢 Low}

Want Baz to fix this for you? Activate Fixer

Other fix methods

Prompt for AI Agents:

In apps/opik-documentation/documentation/fern/docs/tracing/integrations/minimax.mdx around line 190, the single-line example minimax_model = LiteLLMChatModel(model_name="minimax/MiniMax-M2.7") is hand-pasted and missing required metadata. First search the autogenerated SDK/docs and examples for a canonical/generated Minimax example and, if found, replace this line with a link to that canonical example (include the file path/URL and a brief note). If no canonical example exists, expand this snippet by adding: (1) a one-line intent/trigger sentence immediately above it describing when to use the snippet, (2) a minimal runnable context (import and variable assignment) with an inline comment on the same line explaining the observable behavior, and (3) a maintenance note below pointing to the canonical/generated artifact (or state “none”), include the owning team, and an update cadence. Ensure the maintenance note references a repo path or URL rather than vague text.

aadereiko

Hey, thanks for your contribution! The frontend code looks good 🙂
Could you please attach videos of these models in action? That would help us conduct a more thorough review.

octo-patch · 2026-03-24T05:09:51Z

Thanks for the review, @aadereiko! I don't have a video recording setup available, but I can confirm the MiniMax models work through the standard OpenAI-compatible API (https://api.minimax.io/v1). The implementation follows the same pattern as other providers in the codebase.

If it would help, I can add screenshots of the test results or API response examples instead.

andrescrz

Hi @octo-patch

Thanks for the update, really appreciate the contribution here!

Would it be possible to provide some form of proof that this is working end-to-end? A local recording using Opik would usually be enough, but if that’s not feasible, screenshots of test results or example API responses would also work.

On my side, I’ve focused on reviewing the BE part. One thing to flag though: these changes might get overwritten, since LLM providers and models are now heavily automated on our end. To make this sustainable, we’d need to integrate this provider into the automation layer; otherwise, the current implementation may not persist.

We’ll also get someone from the team to finalize the review on the Python SDK part.

andrescrz · 2026-03-24T10:37:31Z

apps/opik-backend/src/main/resources/model_prices_and_context_window.json

This file is automatically synced from lite llm repository. So your changes will be overwritten. If you want cost tracking for these, you'll need to send a PR in that repo first. If accepted, changes will be propagated here.

andrescrz · 2026-03-24T10:37:52Z

apps/opik-frontend/src/data/model_prices_and_context_window.json

Same about this file. It's an automated copy and it will be overwritten.

andrescrz · 2026-03-24T10:44:50Z

...-backend/src/main/java/com/comet/opik/infrastructure/llm/openrouter/OpenRouterModelName.java

This is automated now, we will need a review from @AndreiCautisanu to incorporate these.

andrescrz · 2026-03-24T10:45:23Z

apps/opik-frontend/src/hooks/useLLMProviderModelsData.ts

Same about this, this is automated now @AndreiCautisanu

andrescrz · 2026-03-24T10:45:53Z

apps/opik-frontend/src/types/providers.ts

Same here about the automation. This provider would need to be incorporated to prevent being overwritten. @AndreiCautisanu

octo-patch · 2026-03-25T05:10:38Z

Thank you @andrescrz and @aadereiko for the thorough review!

Regarding the automated files:

I understand that model_prices_and_context_window.json (both backend and frontend), OpenRouterModelName.java, useLLMProviderModelsData.ts, and providers.ts are auto-synced. I'll remove those changes from this PR so they don't conflict with your automation pipeline. The MiniMax model definitions would need to go through LiteLLM upstream first.

Regarding proof of working end-to-end:

I'll prepare test output showing the MiniMax integration working with the Python SDK (LiteLLM path with Opik tracing). Will share that shortly.

Shall I go ahead and trim the PR to only the non-automated files (Python SDK changes, docs, and tests)?

octo-patch requested review from a team as code owners March 15, 2026 12:07

github-actions bot added documentation Improvements or additions to documentation python Pull requests that update Python code tests Including test files, or tests related like configuration. Python SDK labels Mar 15, 2026

baz-reviewer bot reviewed Mar 15, 2026

View reviewed changes

github-actions bot added java Pull requests that update Java code Frontend Backend typescript *.ts *.tsx labels Mar 18, 2026

octo-patch changed the title ~~feat: add MiniMax as a supported LLM provider~~ feat: add MiniMax as a supported LLM provider with M2.7 models Mar 18, 2026

baz-reviewer bot reviewed Mar 18, 2026

View reviewed changes

aadereiko reviewed Mar 23, 2026

View reviewed changes

andrescrz reviewed Mar 24, 2026

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat: add MiniMax as a supported LLM provider with M2.7 models#5666

feat: add MiniMax as a supported LLM provider with M2.7 models#5666
octo-patch wants to merge 2 commits intocomet-ml:mainfrom
octo-patch:feature/add-minimax-integration

octo-patch commented Mar 15, 2026 •

edited

Loading

Uh oh!

baz-reviewer bot Mar 15, 2026

Uh oh!

baz-reviewer bot Mar 15, 2026

Uh oh!

baz-reviewer bot Mar 18, 2026

Uh oh!

aadereiko left a comment •

edited

Loading

Uh oh!

octo-patch commented Mar 24, 2026

Uh oh!

andrescrz left a comment

Uh oh!

andrescrz Mar 24, 2026

Uh oh!

andrescrz Mar 24, 2026

Uh oh!

andrescrz Mar 24, 2026

Uh oh!

andrescrz Mar 24, 2026

Uh oh!

andrescrz Mar 24, 2026

Uh oh!

octo-patch commented Mar 25, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

octo-patch commented Mar 15, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Changes

Why

Testing

Uh oh!

baz-reviewer bot Mar 15, 2026

Choose a reason for hiding this comment

Uh oh!

baz-reviewer bot Mar 15, 2026

Choose a reason for hiding this comment

Uh oh!

baz-reviewer bot Mar 18, 2026

Choose a reason for hiding this comment

Uh oh!

aadereiko left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

octo-patch commented Mar 24, 2026

Uh oh!

andrescrz left a comment

Choose a reason for hiding this comment

Uh oh!

andrescrz Mar 24, 2026

Choose a reason for hiding this comment

Uh oh!

andrescrz Mar 24, 2026

Choose a reason for hiding this comment

Uh oh!

andrescrz Mar 24, 2026

Choose a reason for hiding this comment

Uh oh!

andrescrz Mar 24, 2026

Choose a reason for hiding this comment

Uh oh!

andrescrz Mar 24, 2026

Choose a reason for hiding this comment

Uh oh!

octo-patch commented Mar 25, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

octo-patch commented Mar 15, 2026 •

edited

Loading

aadereiko left a comment •

edited

Loading