DeepSeek-V4-Flash-0731 (Reasoning)

by DeepSeek

DeepSeek-V4-Flash-0731 (Reasoning) is a reasoning model from DeepSeek, released on July 31, 2026. It has a 1M-token context window and can generate up to 1M output tokens. API pricing is $0.06 per 1M input tokens and $0.18 per 1M output tokens.

DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version with substantially stronger agentic capabilities. It retains the V4-Flash architecture and adds an attached DSpark speculative-decoding module for faster inference. The open-weight model supports a 1M-token context window and low, high, and max reasoning-effort levels, and DeepSeek reports that it outperforms the much larger DeepSeek-V4-Pro Preview across its published agent benchmark suite.

Key specs

ProviderDeepSeek
Release date2026-07-31
Licenseopen source
Context window1M tokens
Max output1M tokens
Input price$0.06 / 1M tokens
Output price$0.18 / 1M tokens
Intelligence Score43.3
Coding index31.3

Quick answers

What is the context window of DeepSeek-V4-Flash-0731 (Reasoning)?

DeepSeek-V4-Flash-0731 (Reasoning) has a context window of 1M tokens, with a maximum output of 1M tokens per response.

How much does DeepSeek-V4-Flash-0731 (Reasoning) cost?

DeepSeek-V4-Flash-0731 (Reasoning) costs $0.06 per 1M input tokens and $0.18 per 1M output tokens through the API.

Is DeepSeek-V4-Flash-0731 (Reasoning) open source?

Yes. DeepSeek-V4-Flash-0731 (Reasoning) is an open model released under the open source license.

When was DeepSeek-V4-Flash-0731 (Reasoning) released?

DeepSeek released DeepSeek-V4-Flash-0731 (Reasoning) on July 31, 2026.

Compare on the AI leaderboard · All AI models

More models from DeepSeek