DeepSeekdeepseek-flash

deepseek/deepseek-flash

fastreasoning
Open in Playground

DeepSeek deepseek-flash: the fast, low-cost DeepSeek tier with reasoning tokens reported separately.

Pricing

USD per 1M tokens, billed per token. Cached input applies where the provider caches prompts.

Input
$0.147
Output
$0.590
Cached input
$0.0029

Specifications

Context length
1M
Max output tokens
—
Input
text
Output
text
Endpoints
openai, openai-response, anthropic
Released
Sep 10, 2026
Alias accepted
deepseek-flash

Example request

curl https://api.nxioai.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NXIO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek/deepseek-flash","messages":[{"role":"user","content":"Hello"}]}'

Price history

Every price change opens a new version. Past requests are billed with the version in effect at the time.

EffectiveUntilInputOutputCached inputSource
Oct 6, 2026current$0.147$0.590$0.0029sync