Send a chat completion request to a selected model. The request must contain a “messages” array. All advanced options from the base request are also supported.
The model ID to use. If unspecified, the user’s default is used.
Enable streaming of results.
Maximum number of tokens (range: [1, context_length)).
Sampling temperature (range: [0, 2]).
Seed for deterministic outputs.
Top-p sampling value (range: (0, 1]).
Top-k sampling value (range: [1, Infinity)).
Frequency penalty (range: [-2, 2]).
Presence penalty (range: [-2, 2]).
Repetition penalty (range: (0, 2]).
Mapping of token IDs to bias values.
Number of top log probabilities to return.
Minimum probability threshold (range: [0, 1]).
Alternate top sampling parameter (range: [0, 1]).
List of prompt transforms (OpenRouter-only).
Alternate list of models for routing overrides.
Model routing strategy (OpenRouter-only).
Preferences for provider routing.
Configuration for model reasoning/thinking tokens
Successful completion