[guillaumegay13]

Automated sync between the Manifest gateway and this catalog (modelparams-agent).

How entries are verified: the local gateway loads this branch's catalog; for every declared param and test value the agent configures it through the gateway's model-params API, sends a request through the proxy pinned to the model, and checks the gateway applied the value upstream and got a 200 from that model. Params that fail are removed from the entry before it is filed.

This PR is rebuilt from main on every run and merged automatically once CI is green.

Added (1)

Entry	Params verified	Dropped	Corrected	Cloned from
opencode-go/claude-haiku-5-5-subscription.yaml	max_tokens presence_penalty frequency_penalty response_format.type	temperature top_p top_k	—	opencode-go/deepseek-flash-subscription.yaml

Evidence

models/opencode-go/claude-haiku-5-5-subscription.yaml

• baseline: 200 from opencode-go/opencode-go/claude-haiku-5-5 (subscription)
• max_tokens ✅ 1
• presence_penalty ✅ -2, 2
• frequency_penalty ✅ -2, 2
• response_format.type ✅ "text", "json_object"
• ❌ dropped temperature: temperature=0 → HTTP 400: Upstream request failed: [invalid_request_error] temperature is deprecated for this model.
• ❌ dropped top_p: top_p=0.01 → HTTP 400: Upstream request failed: [invalid_request_error] top_p is deprecated for this model.
• ❌ dropped top_k: top_k=1 → HTTP 400: Upstream request failed: [invalid_request_error] top_k is deprecated for this model.

Needs a human: params now refused (12)

Re-verification found these declared params refused. Not removed — the param guard blocks removals and dropping a param is a maintainer's call.

• models/google/gemma-4-26b-a4b-it.yaml generationConfig.maxOutputTokens generationConfig.temperature generationConfig.topP generationConfig.topK generationConfig.thinkingConfig.thinkingBudget generationConfig.thinkingConfig.includeThoughts generationConfig.responseMimeType: generationConfig.maxOutputTokens=1 → HTTP 400: Thinking budget is not supported for this model. (same error for each)
• models/google/gemma-4-26b-a4b-it.yaml generationConfig.thinkingConfig.thinkingLevel: generationConfig.thinkingConfig.thinkingLevel="minimal" → HTTP 400: You can only set only one of thinking budget and thinking level.
• models/mistral/magistral-small-latest.yaml prompt_mode: prompt_mode="reasoning" → HTTP 400: Reasoning prompt mode is not enabled for this model
• models/mistral/magistral-small-latest.yaml response_format.type: response_format.type="json_schema" → HTTP 400: Schema response format type requires a json_schema
• models/mistral/mistral-large-latest.yaml response_format.type: response_format.type="json_schema" → HTTP 400: Schema response format type requires a json_schema
• models/mistral/mistral-small-latest.yaml response_format.type: response_format.type="json_schema" → HTTP 400: Schema response format type requires a json_schema

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated
modelparams.dev	Ready	Preview	Oct 8, 2026 5:49am UTC