DeepSeek

DeepSeek V4 Flash 0731

Generally availableOpen weights1M contextReasoning

Summary

DeepSeek V4 Flash 0731 is an open-weight language model from DeepSeek, released on 31 Jul 2026. It accepts text and generates text, with a 1M-token context window and up to 384K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.06 per million input tokens and $0.18 per million output tokens (DeepInfra), across 8 providers we track.

Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperDeepSeek
Release date31 Jul 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licensemit [Hugging Face]
Parameters304B [Hugging Face]
Context window1M (1,000,000 tokens) [models.dev]
Max output384K tokens [models.dev]
Knowledge cutoffMay 2025 [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]
Hugging Facedeepseek-ai/DeepSeek-V4-Flash-0731 [Hugging Face]

DeepSeek V4 Flash 0731 API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
DeepInfra
deepseek-ai/DeepSeek-V4-Flash-0731
$0.06$0.18$0.011Mmodels.dev, 18 Nov 2026
OpenRouter
deepseek/deepseek-v4-flash-0731
$0.06$0.18$0.011MOpenRouter, 18 Nov 2026
Baseten
deepseek-ai/DeepSeek-V4-Flash-0731
$0.13$0.26$0.031Mmodels.dev, 18 Nov 2026
Vercel AI Gateway
deepseek/deepseek-v4-flash-0731
$0.13$0.26$0.031Mmodels.dev, 18 Nov 2026
Hugging Face Inference Providers
deepseek-ai/DeepSeek-V4-Flash-0731
$0.14$0.28–1Mmodels.dev, 18 Nov 2026
SiliconFlow
deepseek-ai/DeepSeek-V4-Flash-0731
$0.22$0.66$0.011Mmodels.dev, 18 Nov 2026
Alibaba Cloud Model Studio
deepseek-v4-flash-0731
$0.44$1.32$0.091Mmodels.dev, 18 Nov 2026
Novita AI
deepseek/deepseek-v4-flash-0731
$0.44$1.32$0.031Mmodels.dev, 18 Nov 2026

Running DeepSeek V4 Flash 0731 locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)184 GB186 GB188 GB
Q8_0 (8-bit)323 GB325 GB327 GB
FP16 / BF16 (16-bit)608 GB610 GB612 GB

At 4-bit with an 8K conversation, DeepSeek V4 Flash 0731 needs about 186 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.

Frequently asked questions

What is the context window of DeepSeek V4 Flash 0731?

DeepSeek V4 Flash 0731 has a context window of 1,000,000 tokens (1M) and can generate up to 384,000 tokens in a single response, according to models.dev.

How much does the DeepSeek V4 Flash 0731 API cost?

Through Alibaba Cloud Model Studio, DeepSeek V4 Flash 0731 costs $0.44 per million input tokens and $1.32 per million output tokens. The lowest listed price is $0.06 input / $0.18 output through DeepInfra. Prices last verified 18 Nov 2026.

Is DeepSeek V4 Flash 0731 open source?

DeepSeek V4 Flash 0731 is an open-weight model: its weights are published on Hugging Face as deepseek-ai/DeepSeek-V4-Flash-0731 under the mit license. Check the license terms before commercial use.

When was DeepSeek V4 Flash 0731 released?

DeepSeek released DeepSeek V4 Flash 0731 on 31 Jul 2026, according to models.dev.

Which providers offer DeepSeek V4 Flash 0731?

We track DeepSeek V4 Flash 0731 on 8 providers: DeepInfra, OpenRouter, Baseten, Vercel AI Gateway, Hugging Face Inference Providers, SiliconFlow, Alibaba Cloud Model Studio, Novita AI.

How much VRAM does DeepSeek V4 Flash 0731 need?

About 186 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 325 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Muse Spark 1.2 ContributorMeta21 Aug 20261M$0.10$0.20–
Muse Spark 1.3 ContributorMeta2 Sept 20261M$0.10$0.20–
MiMo-V2.6-FlashXiaomi (MiMo)22 Sept 20261M$0.14$0.28Open
MiniMax-M3.1-FlashMiniMax19 Oct 20261M$0.07$0.30Open
Tencent Hy4 FlashTencent (Hunyuan)16 Nov 20261M$0.04$0.14Open
GLM-5.3-FlashZhipu AI (Z.ai)26 Aug 20261M$0.15$0.50Open

Change history

  • Context window changed from 1M to 1M
  • OpenRouter price changed: input $0.04 → $0.06, output $0.30 → $0.18 per 1M tokens
  • Max output changed from 393K to 384K
  • Max output changed from 384K to 393K
  • Context window changed from 1M to 1M
  • Max output changed from 393K to 384K
  • Context window changed from 1M to 1M
  • Max output changed from 384K to 393K
  • Context window changed from 1M to 1M
  • Context window changed from 1M to 1M
  • Context window changed from 1M to 1M
  • No longer listed on nebius
  • Max output changed from 1M to 384K
  • Context window changed from 1M to 1M
  • Max output changed from 384K to 1M
  • Context window changed from 1M to 1M
  • Context window changed from 1M to 1M
  • No longer listed on cloudflare-workers-ai
  • OpenRouter price changed: input $0.05 → $0.04, output $0.30 → $0.30 per 1M tokens
  • Context window changed from 1M to 1M
  • OpenRouter price changed: input $0.06 → $0.05, output $0.30 → $0.30 per 1M tokens
  • OpenRouter price changed: input $0.05 → $0.06, output $0.30 → $0.30 per 1M tokens
  • Context window changed from 1M to 1M
  • Max output changed from 1M to 384K
  • OpenRouter price changed: input $0.06 → $0.05, output $0.30 → $0.30 per 1M tokens

Sources