Skip to main content

DeepSeek V4 Flash: API pricing, providers and specs

Textby DeepSeekMITReleased Apr 22, 2026

DeepSeek V4 Flash is a text model by DeepSeek. 26 providers serve it, from $0.17 to $1.33 /1M; the lowest price is at Opper.

A newer version is out: DeepSeek V4.1 Flash · released Sep 10, 2026

Lowest price$0.17/1Mat Opper
Maker's price—The maker does not sell it
Providers26
Context1.05MMax output 384K

How DeepSeek V4 Flash compares

Against the 737 text models on the site priced the same way.

  • Cheap for its class: at $0.17 /1M, its lowest price undercuts 86% of comparable models (median $1.10).
  • Its 1.05M-token context window is larger than 83% of them (median 262K), about 1570 pages of text.
  • 26 providers serve it; 93% of comparable models have fewer.
  • Its weights are open under the MIT license: commercial use allowed.

DeepSeek V4 Flash prices by provider

Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.

ProviderInputOutputPrompt cachingContext
Opper$0.07/1M$0.17/1M$0.01/1M—
Hugging Face$0.09/1MFrom$0.18/1M——
Deep Infra$0.09/1MFrom$0.18/1M$0.018/1M—
DevPass (LLM Gateway)$0.08/1MFrom$0.18/1M$0.016/1M—
FastRouter$0.09/1M$0.18/1M$0.018/1M1.05M
OpenRouter$0.091/1MFrom$0.182/1M$0.018/1M1.05M
Vercel AI Gateway$0.13/1M$0.26/1M$0.028/1M1M
Venice AI$0.138/1M$0.275/1M$0.028/1M—
SiliconFlow$0.139/1M$0.278/1M——
Neuralwatt$0.14/1M$0.28/1M$0.03/1M—
Atlas Cloud$0.14/1M$0.28/1M$0.028/1M—
Jiekou.AI$0.14/1M$0.28/1M$0.028/1M—
AIHubMix$0.142/1M$0.284/1M$0.028/1M1M
Kenari$0.152/1M$0.304/1M$0.004/1M—
CometAPI$0.12/1MFrom$0.48/1M——
Impossibl$0.19/1M$0.51/1M$0.028/1M—
ZenMux$0.22/1M$0.66/1M$0.007/1M1M
OrcaRouter$0.22/1M$0.66/1M$0.007/1M1.05M
CrazyRouter$0.23/1M$0.67/1M——
APIMart$0.343/1M$1.03/1M——
CrossModel$0.30/1M$1.20/1M$0.006/1M—
Prime Inference$0.44/1M$1.32/1M——
APIYI$0.44/1MFrom$1.32/1M——
LaoZhang API$0.44/1M$1.32/1M——
BytePlus$0.44/1MFrom$1.32/1M$0.014/1M—
Poe$0.444/1M$1.33/1M$0.028/1M1M
Output price by provider, /1M, cheapest first
  1. Opper$0.17
  2. FastRouter$0.18
  3. Hugging FaceFrom$0.18
  4. Deep InfraFrom$0.18
  5. DevPass (LLM Gateway)From$0.18
  6. OpenRouterFrom$0.182
  7. Vercel AI Gateway$0.26
  8. Venice AI$0.275
  9. SiliconFlow$0.278
  10. Neuralwatt$0.28
  11. Atlas Cloud$0.28
  12. Jiekou.AI$0.28
Prices in US dollars, updated daily from each provider. Prices last checked Oct 25, 2026.

Specs

Type
Text
Maker
DeepSeek
Inputs
Text
Outputs
Text
Context
1.05M≈ 1570 pages of text
Max output
384K
Capabilities
Prompt caching, JSON, Reasoning, Tool calling
Released
Apr 22, 2026
License
MITcommercial use allowed
Open weights
Yes, downloadable
Parameters
291B
Monthly searches
51K
Get the weightsHugging Face936K downloads in 30 days

Alternatives to DeepSeek V4 Flash

Same kind of model from other makers, at a similar price.

ModelLowest priceContextArenaProviders
DeepSeek V4 Flashthis model$0.17/1M1.05M—26
GLM-5.3-Flash$0.20/1M1.05M160845
Qwen3.8 27B$0.50/1M262K159133
GPT-6 Luna$0.40/1M1.05M157828
Claude Haiku 5.5$0.30/1M1M158527
Qwen3.8 Flash Next$0.376/1M262K16285
Ling 3.1 Flash$0.225/1M262K—5
Qwen2-1.5B-Instruct$0.20/1M——2
Qwen3.5 Flash$0.287/1M1M—1

More from DeepSeek

DeepSeek V4.1 FlashDeepSeek$0.03/1MDeepSeek V4 Flash Vision ExpDeepSeek$0.294/1MDeepSeek V4 ProDeepSeek$0.418/1MDeepSeek R1DeepSeek$1.79/1MDeepSeek V3DeepSeek$0.89/1MDeepSeek V4 Flash 0731DeepSeek$0.133/1MDeepSeek R1 Distill Qwen 7BDeepSeek$0.01/1MDeepSeek R1 Distill Qwen 32BDeepSeek$0.20/1M
All 47 DeepSeek models

DeepSeek V4 Flash FAQ

Can't find what you're looking for? Contact us