DEEPSEEK

deepseek-flash

DeepSeek's Flash tier, currently served by DeepSeek-V4.1-Flash-1017, with a 1M-token context window, 384K max output and thinking on by default. Handles vision, tool calls, JSON output and both OpenAI and Anthropic request formats.

Usage billing

Official price vs Nbility

Per 1M tokens, read live from the gateway. Nbility shows its lowest public group.

DeepSeek list price

Input$2.00Output$8.00

Nbility · china-大厂 group

Input1.30Output5.20

Group prices

Every available group is listed with its effective input and output price.

Usage billing
GroupRatioInputOutputCache read price
Base pricex1
2.00/1M
8.00/1M
0.04/1M
china-大厂x0.65
1.30/1M
5.20/1M
0.026/1M

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-flash","messages":[{"role":"user","content":"Hello"}]}'

Compatible endpoints

openaiPOST /v1/chat/completions
openai-responsePOST /v1/responses
openai-response-compactPOST /v1/responses/compact
anthropicPOST /v1/messages
geminiPOST /v1beta/models/{model}:generateContent
openai-alpha-searchPOST /v1/alpha/search

Docs for this model