[BOT ISSUE] Together AI: add missing `Qwen/Qwen3.7-Max` model

[github-actions]

Gap

The Together AI model Qwen/Qwen3.7-Max is missing from packages/proxy/schema/model_list.json. This is Qwen's flagship max-tier chat model, available on Together AI's serverless inference surface.

Official sources

Field	Source	URL
Model ID, listing	Together serverless models page	https://docs.together.ai/docs/serverless-models
Model ID, pricing	Together pricing page	https://www.together.ai/pricing

Verified fields

• Model ID: Qwen/Qwen3.7-Max — confirmed on both serverless models page and pricing page
• Format: openai — Together AI uses OpenAI-compatible API format (same as all other Together models in catalog)
• Flavor: chat — listed under Chat models section on serverless models page
• Available providers: ["together"]

Pricing discrepancy

Two official Together AI sources show different pricing:

Source	Input ($/1M tokens)	Output ($/1M tokens)	Cached input
Serverless models docs	$2.50	$7.50	—
Pricing page (together.ai/pricing)	$1.25	$3.75	$0.13

Because the two official sources disagree, pricing should be verified manually before adding. The pricing page (together.ai/pricing) is likely the more current source.

Fields NOT published

• max_input_tokens: Not specified on serverless models page (shown as "-")
• max_output_tokens: Not specified
• multimodal: Not confirmed
• reasoning: Not confirmed
• displayName: Not officially published; suggest "Qwen 3.7 Max" based on naming pattern

Local files inspected

• packages/proxy/schema/model_list.json — grep for Qwen3.7 returns no matches
• Existing Together AI Qwen models use format openai, flavor chat, and IDs like Qwen/Qwen3.5-397B-A17B, Qwen/Qwen3.6-Plus, Qwen/Qwen3.5-9B

Verification notes

• Cross-source: Model ID confirmed on (1) Together serverless models listing page and (2) Together pricing page — two independent official signals
• Recent commits: Model not present in current model_list.json
• ID format: Qwen/Qwen3.7-Max matches Together AI convention of Org/Model-Name (like Qwen/Qwen3.6-Plus, Qwen/Qwen3.5-397B-A17B)
• No duplicate issue: No existing [BOT ISSUE] references Qwen3.7-Max

{
  "kind": "missing_model",
  "provider": "together",
  "models": ["Qwen/Qwen3.7-Max"],
  "status": "active",
  "model_specs": {
    "Qwen/Qwen3.7-Max": {
      "format": "openai",
      "flavor": "chat",
      "available_providers": ["together"]
    }
  },
  "source_urls": [
    "https://docs.together.ai/docs/serverless-models",
    "https://www.together.ai/pricing"
  ]
}

Summary: Add Qwen/Qwen3.7-Max to the Together AI section of the model catalog. Pricing should be verified manually due to discrepancy between sources. Token limits and multimodal/reasoning capabilities were not published and should be confirmed before adding.

[github-actions]

Prepared catalog updates for Qwen/Qwen3.7-Max. Added models: Qwen/Qwen3.7-Max.

Verification sources: https://docs.together.ai/docs/serverless-models, https://www.together.ai/pricing, https://www.together.ai/models, https://help.aliyun.com/zh/model-studio/user-guide/text-generation
Verified metadata applied:

• Qwen/Qwen3.7-Max: format=openai, flavor=chat, displayName=Qwen3.7 Max, max_input_tokens=1000000, max_output_tokens=not provided, pricing(input/output per 1M)=1.25/3.75, input_cache_read_cost_per_mil_tokens=0.13, providers=together, reasoning=true

Opened #667 to apply the catalog update.