35% offprompt cache

DeepSeek V4 Flash 0731

deepseek-v4-flash-0731

DeepSeek V4 Flash 0731 — 1.04858M token context, up to 131,072 output tokens, prompt caching.

Try in playground Get an API key

Input / output per 1M

$0.143/$0.429

official $0.22 / $0.66

Network fee$0.0010

ProviderDeepSeek

ModalityText

Context

1.0M

Max output

131.1K

Input / 1M

$0.143

Output / 1M

$0.429

Pricing

Input / 1M$0.143$0.22

Output / 1M$0.429$0.66

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-flash-0731",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'