Name: DeepSeek: DeepSeek V4 Flash 0731
Author: deepseek

Question 1

What is DeepSeek V4 Flash 0731?

Accepted Answer

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. This is the GA release of DeepSeek V4 Flash.

Question 2

How much does DeepSeek V4 Flash 0731 cost?

Accepted Answer

DeepSeek V4 Flash 0731 costs $0.08/M input tokens and $0.252/M output tokens, with separate rates for Cache Read at $0.0252/M tokens.

Question 3

What is the context length of DeepSeek V4 Flash 0731?

Accepted Answer

DeepSeek V4 Flash 0731 has a 1,048,576 token context window.

Question 4

Does DeepSeek V4 Flash 0731 support tool calling and structured outputs?

Accepted Answer

Yes. DeepSeek V4 Flash 0731 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Question 5

Which providers serve DeepSeek V4 Flash 0731?

Accepted Answer

DeepSeek V4 Flash 0731 is served by 28 providers on OpenRouter: DigitalOcean, DeepInfra, OpenInference, Decart, Sail Research, GMICloud, StreamLake, Baseten and 20 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

Question 6

When was DeepSeek V4 Flash 0731 released?

Accepted Answer

DeepSeek V4 Flash 0731 was released on 2026-07-31.

DeepSeek: DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731

DeepSeek: DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731

Frequently asked questions

Frequently asked questions