Skip to content
Metered.
DeepSeek model

DeepSeek V4 Flash 0731

API pricing per million tokens

deepseek-v4-flash-0731 Open weightsChecked 8h ago
Cost calculator Compare Benchmarks
Input
$0.053
per 1M, StreamLake (fp8)
Output
$0.158
per 1M tokens
Cached input
$0.0017
no batch tier listed
Context
1.31M
944K max output

Where to buy it (29)

  • StreamLakefp8, fp8$0.053 / $0.158cached $0.0017
  • DeepInfrafp8, fp8$0.06 / $0.18cached $0.015
  • Relacefp4, fp4$0.04 / $0.32cached $0.016
  • Makoradefault region$0.09 / $0.195cached $0.02
  • Waferfast$0.08 / $0.35cached $0.02
  • DigitalOceandefault region$0.119 / $0.238cached $0.024
  • Basetenfp8, fp8$0.13 / $0.26cached $0.028
  • Sail Researchfp4, fp4$0.038 / $0.55cached $0.023
  • CoreWeavefp8, fp8$0.13 / $0.28cached $0.07
  • Coheredefault region$0.14 / $0.28cached $0.07
  • Nebiusfp8, fp8$0.14 / $0.28$0.175 blended
  • Parasailfp8, fp8$0.14 / $0.28cached $0.05
  • Together AIdefault region$0.14 / $0.28cached $0.03
  • Rekafp4, fp4$0.088 / $0.528cached $0.0056
  • Morphdefault region$0.142 / $0.4cached $0.036
  • Venicedefault region$0.175 / $0.35cached $0.035
  • Inceptronfp4, fp4$0.091 / $0.613cached $0.06
  • OpenInferencefp8, fp8$0.14 / $0.7cached $0.03
  • Mancer 2fp8, fp8$0.2 / $0.6$0.3 blended
  • Fireworks AIdefault region$0.22 / $0.66cached $0.007
  • SiliconFlowfp8, fp8$0.22 / $0.66cached $0.028
  • GMICloudfp8, fp8$0.286 / $0.858cached $0.0091
  • NextBitfp8, fp8$0.352 / $1.06cached $0.012
  • Qwen (Alibaba)default region$0.352 / $1.06cached $0.035
  • Novita AIfp8, fp8$0.409 / $1.23cached $0.026
  • AtlasCloudfp4, fp4$0.44 / $1.32cached $0.028
  • Baidufp8, fp8$0.44 / $1.32cached $0.014
  • Cloudflare Workers AIdefault region$0.44 / $1.32cached $0.014
  • Phaladefault region$0.44 / $1.32cached $0.028

Through a gateway

Your own numbers

100M input and 20M output tokens a month: $8.45 direct.

Related models

About DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.

Takes text in and returns text. First listed Sep 23, 2026. Blended price $0.079 per 1M tokens at 3 input to 1 output.

OpenRouter listing DeepSeek pricing page
Across fru.devCompany profile

Questions

How much does DeepSeek V4 Flash 0731 cost?

$0.053 per million input tokens and $0.158 per million output tokens, with cached input at $0.0017.

What is the context window of DeepSeek V4 Flash 0731?

1.31M tokens, with up to 944K tokens of output.

Where is DeepSeek V4 Flash 0731 cheapest?

Of 29 routes tracked, StreamLake is cheapest at $0.053 input and $0.158 output per million tokens.

Has DeepSeek V4 Flash 0731's price changed?

Yes. The output price went from $0.528 to $1.06, first seen Sep 24, 2026.

List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Weekly: LLM API list prices that changed, Thursday mornings.