Creates a model response for the given chat conversation.
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Model ID to use for completion.
claude-sonnet-4-6, claude-sonnet-4-5-20250929, claude-sonnet-4-20250514, claude-opus-4-6, claude-opus-4-5-20251101, claude-opus-4-1-20250805, claude-opus-4-20250514, claude-haiku-4-5-20251001, claude-3-7-sonnet-20250219, claude-3-5-sonnet-20241022, gpt-5-4, gpt-5-3-codex, gpt-5-2, gpt-5-2-chat, gpt-5-2-chat-latest, gpt-5-2-codex, gpt-5-1, gpt-5-1-chat, gpt-5-1-chat-latest, gpt-5-1-codex-mini, gpt-5, gpt-5-chat-latest, gpt-5-pro, gpt-5-codex, gpt-5-codex-high, gpt-5-codex-low, gpt-5-mini, gpt-5-nano, gpt-4o, gpt-4o-mini, gpt-4-1, gpt-4, deepseek-v3-2-speciale, deepseek-v3-2, deepseek-v3-2-exp, deepseek-v3-2-251201, deepseek-v3-1-terminus, deepseek-v3-1, deepseek-v3, qwen3.5-397b-a17b, qwen3-coder-next, qwen3-coder, qwen3-235b-a22b, qwen3-32b, qwen3-14b, qwen2.5-72b-instruct, doubao-seed-2.0-pro, doubao-seed-2.0-code, doubao-seed-2.0-lite, doubao-seed-2.0-mini, doubao-seed-1-8-251228, doubao-seed-1-6-flash-250828, doubao-seed-1-6-251015, doubao-seed-1-6-lite-251015, doubao-seed-1-6-vision-250815, minimax-m2.5, minimax-m2.1, kimi-k2.5, grok-3, grok-3-mini, grok-4-fast-reasoning, grok-4-fast-non-reasoning, grok-4-1-fast-reasoning, grok-4-1-fast-non-reasoning, gemini-3.1-pro-preview, gemini-3.1-flash-image-preview, gemini-3-pro-preview, gemini-3-flash-preview, gemini-2.5-pro, gemini-2.5-flash, gemini-2.0-flash, glm-4-7-251222 "claude-sonnet-4-6"
A list of messages comprising the conversation so far.
1[{ "role": "user", "content": "Hello!" }]
The maximum number of tokens to generate in the chat completion.
x >= 1Sampling temperature between 0 and 2. Higher values make output more random, lower values more deterministic.
0 <= x <= 21
Nucleus sampling threshold. An alternative to temperature.
0 <= x <= 1Penalizes new tokens based on their existing frequency in the text so far.
-2 <= x <= 2Penalizes new tokens based on whether they appear in the text so far.
-2 <= x <= 2If true, partial message deltas will be sent as server-sent events.
Up to 4 sequences where the API will stop generating further tokens.
How many chat completion choices to generate for each input message.
x >= 1An object specifying the format that the model must output. Setting to {"type": "json_object"} enables JSON mode.
A list of tools the model may call. Currently, only functions are supported as a tool.
Controls which (if any) tool is called by the model.
A unique identifier representing your end-user.