DEEPSEEK
deepseek-v4-pro
DeepSeek's V4-Pro flagship, with a 1M-token context window, up to 384K output and selectable low, high or max thinking effort. Built for the hardest reasoning and agentic coding work, without image input.
Usage billing
Official price vs Nbility
Per 1M tokens, read live from the gateway. Nbility shows its lowest public group.
DeepSeek list price
Input$9.00Output$27.00
Nbility · china group
Input1.80Output5.40
Group prices
Every available group is listed with its effective input and output price.
| Group | Ratio | Input | Output | Cache read price |
|---|---|---|---|---|
| Base price | x1 | 9.00/1M | 27.00/1M | 0.30/1M |
| china | x0.2 | 1.80/1M | 5.40/1M | 0.06/1M |
| china-官方key | x0.35 | 3.15/1M | 9.45/1M | 0.105/1M |
| china-大厂 | x0.65 | 5.85/1M | 17.55/1M | 0.195/1M |
Quick start
Replace YOUR_API_KEY with a key from your account.
curl https://api.nbility.ai/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek-v4-pro","messages":[{"role":"user","content":"Hello"}]}'Compatible endpoints
openai
POST /v1/chat/completionsopenai-response
POST /v1/responsesopenai-response-compact
POST /v1/responses/compactanthropic
POST /v1/messagesgemini
POST /v1beta/models/{model}:generateContentopenai-alpha-search
POST /v1/alpha/search