by 0G Foundation
Alibaba's Qwen3.7-Max is a flagship LLM with native function calling and web search tool support. Native 1M-token context window with up to 64K output (64K reasoning-mode output, 256K max reasoning chain). Implicit prompt caching is supported and reported via usage.prompt_tokens_details.cached_tokens.
1M
1,000,000 tokens
66K
65,536 tokens
2.1500 0G
per 1M tokens
6.4700 0G
per 1M tokens
1
chatbot
0G Router normalizes requests and responses across providers for you. All endpoints follow the OpenAI API format.
Endpoint
Code Examples
curl https://router-api.0g.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <YOUR_API_KEY>" \
-d '{
"model": "qwen3.7-max",
"messages": [
{"role": "user", "content": "Hello!"}
],
"stream": true
}'TEE Verification
If the provider runs inside a TEE (Trusted Execution Environment), you can request on-chain signature verification by setting verify_tee. The response will include a tee_verified field in the trace.
# Add verify_tee in the JSON body
{
"model": "qwen3.7-max",
"messages": [{"role": "user", "content": "Hello!"}],
"verify_tee": true
}Provider Routing
Control which provider handles your request using the provider parameter.
{
"model": "qwen3.7-max",
"messages": [{"role": "user", "content": "Hello!"}],
"provider": {
"sort": "latency",
"allow_fallbacks": true
}
}