DeepSeek V4 Pro

Coming soon

deepseek/deepseek-v4-pro

DeepSeek V4 Pro. Thinking on by default.

Chat
1.05M context
393K max output
Tools

Try in Playground Compare

Pricing

Input: $1.32 / 1M tokens
Output: $3.96 / 1M tokens
Cached input: $0.044 / 1M tokens

What it costs

A typical request: 2,000 tokens in, 500 out$0.0046

1,000 of those requests$4.62

Performance on SparrowCodes

Measured from real requests over the last 7 days.

No traffic yet. Speed, latency and success rate appear here once this model has served requests on SparrowCodes; we don't show estimates.

Official benchmarks

Scores published by the model's maker, under their test conditions.

Humanity's Last Exam · no tools42.7%
Humanity's Last Exam · with tools60.0%
Terminal-Bench 2.187.9%
DeepSWE62.7%
Toolathlon-Verified74.1%
AutomationBench · public31.8%
GPQA Diamond90.1%
SWE-bench Verified80.6%
LiveCodeBench93.5%
MMLU-Pro87.5%
BrowseComp83.4%

Source: DeepSeek: V4-Pro release notes (2026-08-13)

Source: DeepSeek: V4-Pro model card (2026-08-13)

Specifications

Type: Chat
Served by: Together AI, DeepSeek
Context window: 1,048,576 tokens
Maximum output: 393,216 tokens
Input types: Text
Tool calling: Supported

Use it

curl https://api.sparrowcodes.com/v1/chat/completions \
  -H "Authorization: Bearer $SPARROW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-pro",
    "messages": [{"role": "user", "content": "Explain rate limiting in one paragraph."}]
  }'