01
Model routing
Switch between leading Chinese providers without rebuilding client code.
DeepSeekQwenGLMKimi豆包Llama
Chinese LLMs through one OpenAI-compatible gateway
One API key,
route every model
Connect once and route requests across DeepSeek, Qwen, Kimi, GLM, Doubao and other leading Chinese models. Keep OpenAI-compatible payloads, request logs, and clear operational visibility.
200 OK
POST /v1/chat/completions
Request
curl -X POST "/v1/chat/completions" \
-H "Authorization: Bearer sk-••••" \
-d '{
"model": "your-model",
"messages": [
{ "role": "user", "content": "..." }
]
}'Response
{
"choices": [{ "message": { "content": "Chat request routed." } }],
"usage": { "total_tokens": 27 }
} 142 ms ·27 tokens ·$0.00081
STREAM ·SSE
POST /v1/responses
Request
curl -X POST "/v1/responses" \
-H "Authorization: Bearer sk-••••" \
-d '{
"model": "your-model",
"input": "..."
}'Response
{
"output": [{ "type": "output_text", "text": "Response workflow ready." }],
"usage": { "total_tokens": 31 }
} 168 ms ·31 tokens ·$0.00093
STREAM ·SSE
POST /v1/messages
Request
curl -X POST "/v1/messages" \
-H "Authorization: Bearer sk-••••" \
-d '{
"model": "your-model",
"messages": [
{ "role": "user", "content": "..." }
]
}'Response
{
"content": [{ "type": "text", "text": "DeepSeek message routed." }],
"usage": { "input_tokens": 11, "output_tokens": 18 }
} 156 ms ·29 tokens ·$0.00087
STREAM ·SSE
Platform capabilities
A cleaner route
from prototype to production.
02
Governed access
Manage channels, quotas and keys from one operational layer.
Load balancingRate limitsCost tracking
03
Stable delivery
Route traffic through available regions with latency and reliability in mind.
USCNAPACEU
04
Developer workflow
Keep familiar request formats while adding pricing, logs and provider choice.
APISDKCLIDocs
Workflow
Integrate once. Operate clearly.
1
Set your channel policy
Create keys, choose providers and define the routing behavior for each workload.
2
Call the unified endpoint
Use familiar OpenAI-style requests for chat, responses and provider-specific message APIs.
3
Track every request
Review latency, token usage and cost signals from the same console.
Latest articles
All articles → 8/15/2026
LLM APIs for Research Tools: Summaries, Literature Review, Citations, and Search
Explore LLM API use cases for research tools, including literature review, paper summaries, citation-aware search, note synthesis, and quality controls.
8/10/2026
What Enterprise Buyers Ask Before Approving an LLM API Product
Prepare for enterprise LLM API procurement questions about security, compliance, vendors, data retention, audit logs, SLAs, pricing, and support.
8/9/2026
LLM API Margin Protection for AI SaaS Products
Learn how AI SaaS teams protect margins with model routing, quotas, plan design, usage alerts, premium model controls, and cost per customer analysis.