由 0G Foundation 提供
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 個詞元
8K
8,192 個詞元
$1.5
$0.08
每 1M 詞元
$6
$0.48
每 1M 詞元
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 驗證
使用 verify_tee 請求鏈上簽章驗證。回應的追蹤中包含 tee_verified 欄位。
{
"model": "0gm-1.0-35b-a3b-sia",
"messages": [{"role": "user", "content": "Hello!"}],
"verify_tee": true
}供應商路由
使用 X-0G-Provider-* 請求標頭，控制哪個供應商處理您的請求。
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!"}]
}'僅限私人模型
此模型為私密模型。若要將請求固定至 TEE 支援的供應商，請加上 X-0G-Provider-Trust-Mode: private 標頭。此為選擇性設定，並非預設套用。
X-0G-Provider-Trust-Mode: private