已驗證聊天
Hunyuan-4-preview
由 0G Foundation 提供
Tencent Hunyuan Hy4 preview; 770B total / 49B active MoE tuned for agent, coding and production workflows — stronger task decomposition, long-horizon tool use and long-chain execution than Hunyuan 3. Served via Tencent Cloud MaaS (TokenHub), which exposes both OpenAI and Anthropic faces. Text in / text out, 1M context, up to 64K output. Deep thinking is on by default and can be disabled with reasoning_effort:"none" (enable_thinking is not honored); function calling, JSON mode (response_format: json_object / json_schema) and implicit prompt caching supported.
openaianthropic工具呼叫模態
上下文
1M
1,000,000 個詞元
最大輸出
66K
65,536 個詞元
輸入
$0.834
每 1M 詞元
輸出
$2.501
每 1M 詞元
供應商
2 個端點，分屬 2 個供應商Tencent (CN)TEE（dstack）TeeTLS
輸入 / 100 萬
$0.834 ·4.30000G/M
輸出 / 1M
$2.501 ·12.91000G/M
快取讀取 / 100 萬
$0.0417 ·0.21500G/M
Tencent (CN)TEE（dstack）TeeTLS
輸入 / 100 萬
$0.834 ·4.30990G/M
輸出 / 1M
$2.501 ·12.93000G/M
快取讀取 / 100 萬
$0.0417 ·0.21550G/M
API
POSThttps://router-api.0g.ai/v1/chat/completions
curl "https://router-api.0g.ai/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <YOUR_API_KEY>" \
-d '{
"model": "hy4-preview",
"messages": [
{"role": "user", "content": "Hello!"}
],
"stream": true
}'其他功能
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": "hy4-preview",
"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。
X-0G-Provider-Address 固定供應商；X-0G-Provider-Identity 固定要透過該供應商的哪個上游進行路由。這兩個值都來自 GET /v1/providers 回應中的 address 與 provider_identity 欄位。兩者搭配即可指定某個供應商的特定上游。若兩者都不傳送，路由會依價格與健康狀況挑選，和先前完全相同。
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": "hy4-preview",
"messages": [{"role": "user", "content": "Hello!"}]
}'