RouterLab
Back to catalog
Publisher : DeepSeekFamily : DeepSeekAvailableNo subscriptionHigh availability

DeepSeek V4.1 Flash API

Model ID : deepseek-v4.1-flash

Model ID

deepseek-v4.1-flash

OpenAI-compatible API

Context window

1,000,000 tokens

Maximum output

384,000 tokens

Input / 1M tokens

0.25 USD

Output / 1M tokens

1.15 USD

Cache read / 1M tokens

$0.006

Cache write / 1M tokens

$0.03

Cache reads reuse stored tokens; cache writes create the provider cache.

Access to this model

Authorized plans : bronze, gold, silver, pro, business

This model is also available with credits without a subscription.

Compare plansNo subscriptionTry for freeMake my first API call

Published capabilities

  • Vision
  • Tool calling
  • Streaming
  • Structured
  • Reasoning

Minimal request

curl https://api.routerlab.ch/v1/chat/completions \
  -H "Authorization: Bearer $ROUTERLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-v4.1-flash","max_tokens":128,"messages":[{"role":"user","content":"Hello RouterLab"}]}'

Related models

Other models in this family · DeepSeek

DeepSeek V4.1 Flash

deepseek-v4.1-flash-trial