DeepSeek Flash

Coming soon

deepseek/deepseek-flash

DeepSeek V4.1 Flash. Thinking on by default; set reasoning_effort to none to turn it off.

Chat
1.05M context
393K max output
Vision
Tools

Try in Playground Compare

Pricing

Input: $0.30 / 1M tokens
Output: $1.20 / 1M tokens
Cached input: $0.006 / 1M tokens

What it costs

A typical request: 2,000 tokens in, 500 out$0.0012

1,000 of those requests$1.20

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 tools42.6%
Terminal-Bench 4.042.3%
DeepSWE v1.177.0%
AutomationBench · v1.0.660.5%
Chartography · with tools83.0%

Source: DeepSeek: V4.1-Flash-1017 release notes (2026-10-17)

Specifications

Type: Chat
Served by: Together AI, Fireworks, DeepSeek
Context window: 1,048,576 tokens
Maximum output: 393,216 tokens
Input types: Text, Image
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-flash",
    "messages": [{"role": "user", "content": "Explain rate limiting in one paragraph."}]
  }'