DeepSeek

Models served by DeepSeek

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	Latency	Throughput
DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731:deepseek	1.0M	$0.23/M	$0.69/M	$0.0073/M	N/A	0.9s	78 tps
DeepSeek V4 Flash 0731 (Thinking) deepseek/deepseek-v4-flash-0731:thinking:deepseek	1.0M	$0.23/M	$0.69/M	$0.0073/M	N/A	0.9s	78 tps
DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813:deepseek	1.0M	$0.69/M	$2.08/M	$0.02/M	58%	1.3s	33 tps
DeepSeek V4 Pro 0813 (Thinking) deepseek/deepseek-v4-pro-0813:thinking:deepseek	1.0M	$0.69/M	$2.08/M	$0.02/M	51.3%	1.3s	33 tps

Prices are per million tokens and include the 5% provider-selection markup. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using DeepSeek via the API

Append :deepseek to the model ID, set "provider": "deepseek" in the request body, or send an X-Provider: deepseek header. Explicit provider selection adds a 5% markup over that provider's base price; the prices in the table above already include it.

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-flash-0731:deepseek",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

See the API documentation for provider preferences, price-aware routing, and error behavior.