Chat Completions
POST /v1/chat/completions
Create a model response for the given conversation. Supports multi-turn conversations, streaming, function calling, and both mainstream vendor models and DeepAILab smart-route products.
Endpoint
POST https://deepailab.ai/v1/chat/completionsRequest Example
curl https://deepailab.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $DEEPAILAB_API_KEY" \
-d '{
"model": "claude-sonnet-4-6",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Summarize the three key factors to consider when choosing a production model."}
],
"temperature": 0.7,
"max_tokens": 1000
}'Request Parameters
| Parameter | Type | Required | Complete reference for all DeepAILab API endpoints. Each endpoint includes parameters, code examples, and response formats. |
|---|---|---|---|
| model | string | Required | Model ID to use, e.g. claude-sonnet-4-5, gpt-5.3-codex, gemini-3-flash, deepai-chat, or deepailab-sup |
| messages | array | Required | List of messages with role and content |
| temperature | number | Optional | Sampling temperature 0-2, default 1. Lower is more deterministic |
| max_tokens | integer | Optional | Maximum tokens to generate |
| stream | boolean | Optional | Enable streaming output, default false |
Response Example
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"created": 1704067200,
"model": "claude-sonnet-4-6",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "When selecting a model, compare quality, latency, and cost. Favor higher-quality models for coding and complex reasoning, optimize for latency in high-throughput scenarios, and then balance price with context window size for production."
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 25,
"completion_tokens": 150,
"total_tokens": 175
}
}Supported Models
claude-sonnet-4-6
Anthropic
Vendor flagship
gpt-5.3-codex
OpenAI
Vendor flagship
gemini-3-flash
Google
Vendor multimodal flagship
deepailab-dal
DeepAILab
Smart route product
deepseek-chat
DeepSeek
Vendor reasoning
deepai-chat
DeepAILab
Smart route product
deepai-coder
DeepAILab
Smart route product
deepailab-sup
DeepAILab
System product route
gemini-3-flash
Google
Vendor fast path
These are representative examples only. Query /v1/models/catalog for the live catalog with vendor and brand metadata.