Create a chat completion
Creates a model response for the given conversation. Supports streaming via SSE, tool calling, and multi-modal input (text, images, files).
Authorizations
Enter the API key with the Bearer: prefix, e.g. "Bearer "
Path Parameters
The workspace ID
^[a-f0-9]{24}$Body
Model ID
"openai/gpt-5"
Array of conversation messages
Enable SSE streaming
Maximum tokens to generate
Maximum completion tokens (OpenAI-style)
Sampling temperature (0-2)
Nucleus sampling parameter
Top-K sampling parameter
Frequency penalty (-2 to 2)
Presence penalty (-2 to 2)
Repetition penalty
Random seed for deterministic output
Number of completions to generate
x >= 1Stop sequences
Token ID to bias mapping
Return log probabilities
Number of top log probabilities to return
Minimum probability parameter
Top-A sampling parameter
Reasoning configuration
Reasoning effort level
Output modalities
image, text Legacy function definitions
Tool definitions for function calling
none, auto, required Allow parallel tool calls
Response format specification
Predicted output for latency optimization
Additional metadata
Store the completion
Service tier
End-user identifier
