Long-context reasoning for coding, research and document workflows.
API ID
Kimi-K3.1-ProOverview
- Context
- 1,000,000 tokens
- Max output
- 16,384 tokens
- Input
- Text
- Output
- Text
- Providers
- Azure AI Foundry
- Latest operational check
- Healthy
- API compatibility
- OpenAI Chat Completions
Recommended for
- General-purpose reasoning
- Long-context analysis
- Production assistants
Keep in mind: Supports text Chat Completions with default reasoning and a 16K output limit. Tools, images, Responses, Messages and long-context requests are unavailable.
Supported features
- Function calling: Not supported
- Structured outputs: Not supported
- Vision: Not supported
- Streaming: Supported
- Reasoning: Supported
- Prompt caching: Not supported
Supported parameters
View API reference streamMake your first request
View full setupcurl --fail-with-body https://gateway.primexos.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"Kimi-K3.1-Pro","messages":[{"role":"user","content":"Hello from Primex"}],"stream":false}'Executing this request uses your account’s API credits.