[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
alibaba/deepseek-v4.1-flash-1017.yaml	max_completion_tokens temperature top_p extra_body.top_k extra_body.enable_thinking extra_body.thinking_budget	—	—	alibaba/deepseek-v4.1-flash.yaml

Evidence

models/alibaba/deepseek-v4.1-flash-1017.yaml

• baseline: 200 from qwen/deepseek-v4.1-flash-1017 (api_key)
• max_completion_tokens ✅ 1
• temperature ✅ 0, 1.9
• top_p ✅ 0, 1
• extra_body.top_k ✅ 20, 0
• extra_body.enable_thinking ✅ true, false
• extra_body.thinking_budget ✅ 1

Needs a human: params now refused (5)

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

• models/mistral/ministral-3b-latest.yaml response_format.type: response_format.type="json_schema" → HTTP 400: Schema response format type requires a json_schema
• models/mistral/ministral-8b-latest.yaml response_format.type: response_format.type="json_schema" → HTTP 400: Schema response format type requires a json_schema
• models/mistral/mistral-large-2512.yaml response_format.type: response_format.type="json_schema" → HTTP 400: Schema response format type requires a json_schema
• models/nvidia/glm-5.3-flash.yaml seed: seed=18446744073709552000 → HTTP 400: Failed to deserialize the JSON body into the target type: invalid type: floating point 1.8446744073709552e+19, expected i64 at line 1 column 176
• models/xai/grok-4.3.yaml response_format.type: response_format.type="json_schema" → HTTP 422: Upstream provider rejected the request

[vercel]

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

Project	Deployment	Actions	Updated
modelparams.dev	Ready	Preview	Oct 19, 2026 5:48am UTC