by 0G Foundation
Zhipu AI GLM-5.3 for long-horizon reasoning, coding, and agentic tool use; 1M context, up to 131K output. Deep thinking is always on and cannot be disabled; how reasoning depth is controlled depends on the provider (top-level reasoning_effort or chat_template_kwargs). Function calling, JSON mode (response_format: json_object), and implicit prompt caching supported.
1M
1,048,576 tokens
131K
131,072 tokens
$1.4
per 1M tokens
$4.4
per 1M tokens
curl "https://router-api.0g.ai/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <YOUR_API_KEY>" \
-d '{
"model": "glm-5.3",
"messages": [
{"role": "user", "content": "Hello!"}
],
"stream": true
}'TEE Verification
Request on-chain signature verification with verify_tee. The response includes a tee_verified field in the trace.
{
"model": "glm-5.3",
"messages": [{"role": "user", "content": "Hello!"}],
"verify_tee": true
}Provider Routing
Control which provider handles your request using the X-0G-Provider-* request headers.
curl "https://router-api.0g.ai/v1/chat/completions" \
-H "Authorization: Bearer <YOUR_API_KEY>" \
-H "Content-Type: application/json" \
-H "X-0G-Provider-Address: <PROVIDER_ADDRESS>" \
-H "X-0G-Provider-Identity: <UPSTREAM>" \
-H "X-0G-Provider-Sort: latency" \
-H "X-0G-Provider-Allow-Fallbacks: true" \
-d '{
"model": "glm-5.3",
"messages": [{"role": "user", "content": "Hello!"}]
}'Private models only
This model is Private. To pin requests to a TEE-backed provider, add the X-0G-Provider-Trust-Mode: private header. Opt-in — not applied by default.
X-0G-Provider-Trust-Mode: private