DeepSeek V4.1 Flash 1017 API

Model id: deepseek/deepseek-v4.1-flash-1017.

A chat model with a context window of 1M tokens, called through Hyperouter's OpenAI-compatible API.

Price

Prices per 1M tokens: input / cached input / output.

ModelContextPrice
deepseek/deepseek-v4.1-flash-10171M$0.15 / $0.003 / $0.60

The deepseek/ models have one rate at every prompt length, reason before they answer by default (reasoning_effort: "none" turns it off), and count their reasoning in max_tokens, at most 384,000.

Call it with the OpenAI SDK

Set HYPEROUTER_API_KEY to an API key from the dashboard. Any OpenAI SDK works once its base URL is https://api.hyperouter.app/v1.

curl https://api.hyperouter.app/v1/chat/completions \
  -H "Authorization: Bearer $HYPEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4.1-flash-1017",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Reference

Sign in with Google or GitHub, create an API key, and open a top-up ticket to add credits. You are charged at the provider's list price.