35% offprompt cache

DeepSeek V4.1 Flash 1017

deepseek-v4.1-flash-1017

DeepSeek V4.1 Flash (2026-10-17 build) — 1.05M token context, up to 393,216 output tokens, text / image input, prompt caching.

Try in playground Get an API key

Input / output per 1M

$0.098/$0.39

official $0.15 / $0.6

Network fee$0.0010

ProviderDeepSeek

ModalityText, Image

Context

1.1M

Max output

393.2K

Input / 1M

$0.098

Output / 1M

$0.39

Pricing

Input / 1M$0.098$0.15

Output / 1M$0.39$0.6

Network fee$0.0010per request

35% below the official upstream price.

Request

POST /v1/chat/completions

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