by 0G Foundation
A 35B hybrid MoE model enhanced with per-token reward guidance. At each decoding step, a 4B Value Model scores candidate tokens and steers generation toward higher-quality outputs, with improvements in harmlessness, helpfulness, and honesty.
33K
32,768 tokens
8K
8,192 tokens
$1.5
$0.08
per 1M tokens
$6
$0.48
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": "0gm-1.0-35b-a3b-sia",
"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": "0gm-1.0-35b-a3b-sia",
"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-Sort: latency" \
-H "X-0G-Provider-Allow-Fallbacks: true" \
-d '{
"model": "0gm-1.0-35b-a3b-sia",
"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