Create Chat Completion
Query
Comma-separated response fields to include.
Body
Model ID to use
Conversation messages (at least one item)
Maximum tokens to generate
Sampling temperature (0-2)
Nucleus sampling threshold (0-1)
Penalize repeated tokens (-2 to 2)
Penalize tokens already in text (-2 to 2)
Whether to return log probabilities
Stop sequence string or JSON array of up to 16 sequences
Enable streaming response
Include usage chunks before [DONE] when stream=true
Reasoning mode type
Response format type
JSON array of tool/function definitions for function calling
Tool choice mode or JSON object
Number of most likely tokens to return (requires logprobs=true)
Role of each message
Content of each message
Optional participant name
Tool call ID for tool-role messages
Tool type
Function definition object
Function name
Function description
JSON Schema describing function parameters
Enable strict schema adherence
Response format object