chore(catalog): sync from gateway — 0 added, 2 corrected, 3 retired

[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.

Corrected (2)

Existing entries re-verified through the gateway (daily rotation). A declared bound was refused by the vendor and one step inside was accepted; or enum values were refused by the vendor and the corrected list (refused values removed, values the vendor lists as supported added) was served to the gateway on a draft catalog and every value passed.

• models/xai/grok-4.20-0309-non-reasoning.yaml
  • top_p: declared min 0 refused (HTTP 400: top_p must be positive but top_p = 0); 0.01 accepted → min corrected to 0.01
• models/xai/grok-4.20-0309-reasoning.yaml
  • top_p: declared min 0 refused (HTTP 400: top_p must be positive but top_p = 0); 0.01 accepted → min corrected to 0.01

Needs a human: params now refused (20)

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

• models/alibaba/kimi-k3.yaml temperature: temperature=1.9 → HTTP 400: <400> InternalError.Algo.InvalidParameter: Parameter 'temperature'=1.9 is not supported for kimi-k3 model.
• models/alibaba/kimi-k3.yaml top_p: top_p=0 → HTTP 400: <400> InternalError.Algo.InvalidParameter: Parameter 'top_p'=0.0001 is not supported for kimi-k3 model.
• models/google/gemma-4-31b-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-4-31b-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/glm-5-2.yaml response_format.type: response_format.type="json_schema" → HTTP 400: ThirdPartyException - {"error":{"message":"When response_format type is 'json_schema', the 'json_schema' field must be provided. (parameter=response_format)","t
• models/mistral/ministral-3b-2512.yaml response_format.type: response_format.type="json_schema" → HTTP 400: Schema response format type requires a json_schema
• models/mistral/ministral-8b-2512.yaml response_format.type: response_format.type="json_schema" → HTTP 400: Schema response format type requires a json_schema
• models/mistral/mistral-small-2603.yaml response_format.type: response_format.type="json_schema" → HTTP 400: Schema response format type requires a json_schema
• models/nvidia/laguna-xs-2.1.yaml seed: seed=18446744073709552000 → HTTP 400: invalid type: floating point 1.8446744073709552e+19, expected i64
• models/openai/gpt-4.yaml reasoning_effort: reasoning_effort="low" → HTTP 400: Unrecognized request argument supplied: reasoning_effort
• models/openai/gpt-4.yaml response_format.type: response_format.type="json_schema" → HTTP 400: Missing required parameter: 'response_format.json_schema'.
• models/openai/gpt-4.yaml tool_choice: tool_choice="auto" → HTTP 400: Invalid value for 'tool_choice': 'tool_choice' is only allowed when 'tools' are specified.
• models/xai/grok-4.20-0309-non-reasoning.yaml response_format.type: response_format.type="json_schema" → HTTP 422: Upstream provider rejected the request
• models/xai/grok-4.20-0309-reasoning.yaml response_format.type: response_format.type="json_schema" → HTTP 422: Upstream provider rejected the request

Marked retired (3)

No longer listed by the provider's live /models for N consecutive daily runs.

• models/openai/gpt-5.3-codex-spark-subscription.yaml (missing n/a — not served runs)
• models/openai/gpt-5.4-mini-subscription.yaml (missing n/a — not served runs)
• models/openai/gpt-5.4-subscription.yaml (missing n/a — not served runs)

[vercel]

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

Project	Deployment	Actions	Updated
modelparams.dev	Ready	Preview	Sep 29, 2026 5:48am UTC