Chat
Multi-Provider LLM Gateway
chat/completions endpoint provides a unified, OpenAI-compatible interface to multiple Large Language Models (LLMs), including GPT-4o, Claude 3.5 Sonnet, Gemini 1.5 Pro, and open-source models.Supported Providers
API Specification
API Specification
https://api.chainhub.tech/v1 and use your ChainHub API key.Request Examples
Basic Request
Streaming Request
Response Format
chat.completion object structure.{
"id": "chatcmpl-123",
"object": "chat.completion",
"created": 1677652288,
"model": "gpt-4o",
"choices": [{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I help you today?"
},
"finish_reason": "stop"
}],
"usage": {
"prompt_tokens": 9,
"completion_tokens": 12,
"total_tokens": 21
}
}Best Practices
Context Management
messages array to maintain context. For long conversations, consider using the Embeddings API for retrieval-augmented generation (RAG).Streaming
stream: true for real-time token delivery in user-facing applications.Advanced Configuration
Modified at 2026-02-08 08:34:50