DeepSeek V4 Flash 0731, the DeepSeek model in numbers

What you need to know

DeepSeek released DeepSeek V4 Flash 0731 on July 31, 2026. It has a reasoning mode: it can "think" before answering, which helps with multi-step problems but uses more tokens, and therefore more money. It is an open-weight model: you can host it yourself on infrastructure you control, and 54 API providers listed on models.dev also offer it. That makes it 3 months old as of October 22, 2026.

We file it under open-weight models (68 models in this category on the site).

Measured performance

According to results published by Epoch AI (checked on October 22, 2026), DeepSeek V4 Flash 0731 has a capability index of 68.2 out of 100, computed on 4 benchmarks from our basket.

It is not among the top 30 of the weekly ranking.

• GPQA Diamond (PhD-level science questions): 91% — the best tracked model, Gemini 4 Argon, reaches 96.4%
• OTIS Mock AIME (competition mathematics problems): 94.4% — the best tracked model, GPT-5.5 Pro, reaches 100%
• FrontierMath (very hard research-level mathematics): 57.5% — the best tracked model, GPT-6 Astra, reaches 93.7%
• FrontierCode (advanced programming tasks): 18.8% — the best tracked model, Claude Opus 5.5, reaches 54.6%

What it can do

Its context window reaches 1,000,000 tokens, roughly 1,500 pages of text at 500 words per page: enough to load a whole book or a mid-sized codebase. A single answer can run to 50,000 tokens.

It accepts as input: text. Its knowledge stops at May 2025: beyond that, it needs web search or your documents.

It can call tools (functions, APIs) and return structured JSON output, which makes it a possible foundation for an AI agent.

The weights are published on Hugging Face (deepseek-ai/DeepSeek-V4-Flash-0731): 304.2 billion parameters, mit license and 4,297,931 downloads over the last 30 days. See also our list of open-source models.

What it costs

DeepSeek V4 Flash 0731 costs $0.14 per million input tokens and $0.28 per million output tokens (median of 54 providers, checked on October 22, 2026).

In practice, an agent task that reads 20,000 tokens and writes 2,000 costs about $0.003, or $3.36 for 1,000 such tasks.

That is 3.6 times cheaper than the median output price of open-weight models ($1).

To estimate your own budget, use the agent cost calculator.

What is it good for?

Given its category, DeepSeek V4 Flash 0731 is mainly aimed at projects where you want control over your data or hosting, or want to adapt the model to your field.

Its very large context window makes it worth considering for analysing large sets of documents in a single request.

Its very low cost (under half a cent for our sample task) means it can be called thousands of times a day.

Before adopting it, test it on your own examples: benchmarks measure standard tasks, not your job.

Comparable models

In the same category, the models closest to DeepSeek V4 Flash 0731 are:

• GLM-4.7 (Zhipu AI (Z.ai), index 68.4)
• Kimi K2 Thinking (Moonshot AI, index 69.6)
• Kimi K2.7 Code (Moonshot AI, index 66.7)
• GLM-5.2 (Zhipu AI (Z.ai), index 70.5)