Skip to content
LLMs
DeepSeek logo

DeepSeek: DeepSeek V4 Flash 0731

by DeepSeek

DeepSeek: DeepSeek V4 Flash 0731 is a large language model from DeepSeek. It costs $0.060 per million input tokens and $0.120 per million output tokens. Its context window is 1.3M tokens.

ReasoningTool callingStructured outputPrompt cachingBatch tierOpen weights
Input / 1M tokens
$0.060
Output / 1M tokens
$0.120
Cached input / 1M
$0.012

On repeated prefixes

Context window
1.3M

tokens

Who serves it cheapest

27 hosts serve DeepSeek V4 Flash 0731. Same weights, same API - the price difference is pure margin and routing.

Providers serving DeepSeek: DeepSeek V4 Flash 0731, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
OpenInferenceCheapestfp8$0.040$0.1001.0M-98.8%
Relacefp4$0.060$0.1201.0M-99.5%
StreamLakefp8$0.057$0.1721.0M-97.7%
DeepInfrafp8$0.060$0.1801.0M-99.7%
Inceptronfp4$0.064$0.1731.0M-99.7%
Makora$0.090$0.1951M-98.0%
Wafer$0.100$0.2501.0M-99.3%
Sail Researchfp4$0.074$0.3421.0M-99.5%
DigitalOcean$0.119$0.2381.0M-99.8%
BaseTenfp8$0.130$0.2601.0M-100.0%
CoreWeavefp8$0.130$0.280262K-100.0%
Together$0.140$0.2801.0M-97.6%
Parasailfp8$0.140$0.2801.0M-99.4%
Morphbf16$0.123$0.3481.0M-99.1%
Venice$0.175$0.3501M-99.1%
Rekafp4$0.110$0.660262K-99.6%
Alibaba$0.176$0.5281M-100.0%
Mancer 2fp8$0.200$0.6001.0M-98.1%
Fireworks$0.220$0.6601.0M-98.2%
SiliconFlowfp8$0.220$0.6601.0M-93.5%
GMICloudfp8$0.286$0.8581.0M-99.9%
Phala$0.308$0.9241.0M-99.8%
NextBitfp8$0.352$1.061.0M-99.7%
Novitafp8$0.409$1.231.0M-100.0%
Baidufp8$0.440$1.321.0M-99.8%
AtlasCloudfp4$0.440$1.321.0M-99.9%
Cloudflare$0.440$1.321.3M-100.0%

The spread between OpenInference and Cloudflare is 12× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index
34.5
Coding index
69.1
Agentic index
41.7

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. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

Specifications

DeepSeek: DeepSeek V4 Flash 0731 specifications
Model IDdeepseek/deepseek-v4-flash-0731
ProviderDeepSeek
Context window1.3M tokens
Max output944K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff-
Open weightsYes - deepseek-ai/DeepSeek-V4-Flash-0731
ReleasedJuly 31, 2026

Cheaper alternatives

Models that cost less than DeepSeek V4 Flash 0731 while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does DeepSeek: DeepSeek V4 Flash 0731 cost?

$0.060 per million input tokens and $0.120 per million output tokens. Cached input reads cost $0.012 per million tokens.

What is the context window of DeepSeek: DeepSeek V4 Flash 0731?

1.3M tokens, with up to 944K tokens of output per request.

Which provider serves DeepSeek: DeepSeek V4 Flash 0731 cheapest?

OpenInference at $0.040 per million input tokens - 12× cheaper than Cloudflare, the most expensive of the 27 hosts serving it.

Confirm against the source: DeepSeek official pricing.