128K contextTool callingReasoning

Pricing

USD per 1M tokens · as of 17 August 2026
Input$0.10
Output$0.25
Cached input$0.01

Flat rate — every request bills the same. Full catalog and comparisons on the pricing comparison page.

Where it fits

The cheapest reasoning model in the catalog. High-volume, cost-sensitive workloads — classification, extraction, triage — where a reasoning trace still helps.

Not sure? BiOS Adaptive routes to the best model per request, including this one.

Call it now — OpenAI-compatible
curl https://api.runbios.ai/v1/chat/completions \
  -H "Authorization: Bearer $BIOS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

Existing OpenAI SDK code works by changing the base URL to https://api.runbios.ai/v1 and the key. API overview

More from DeepSeek