DeepSeek-V3.1

by DeepSeek

DeepSeek-V3.1 is a model from DeepSeek, released on January 10, 2025. It has a 164K-token context window and can generate up to 164K output tokens. API pricing is $0.25 per 1M input tokens and $0.95 per 1M output tokens.

DeepSeek-V3.1 is a hybrid model supporting both thinking and non-thinking modes through different chat templates. Built on DeepSeek-V3.1-Base with a two-phase long context extension (32K phase: 630B tokens, 128K phase: 209B tokens), it features 671B total parameters with 37B activated. Key improvements include smarter tool calling through post-training optimization, higher thinking efficiency achieving comparable quality to DeepSeek-R1-0528 while responding more quickly, and UE8M0 FP8 scale data format for model weights and activations. The model excels in both reasoning tasks (thinking mode) and practical applications (non-thinking mode), with particularly strong performance in code agent tasks, math competitions, and search-based problem solving.

Key specs

ProviderDeepSeek
Release date2025-01-10
Licenseopen source
Context window164K tokens
Max output164K tokens
Input price$0.25 / 1M tokens
Output price$0.95 / 1M tokens
Intelligence Score22
Coding index12.4

Quick answers

What is the context window of DeepSeek-V3.1?

DeepSeek-V3.1 has a context window of 164K tokens, with a maximum output of 164K tokens per response.

How much does DeepSeek-V3.1 cost?

DeepSeek-V3.1 costs $0.25 per 1M input tokens and $0.95 per 1M output tokens through the API.

Is DeepSeek-V3.1 open source?

Yes. DeepSeek-V3.1 is an open model released under the open source license.

When was DeepSeek-V3.1 released?

DeepSeek released DeepSeek-V3.1 on January 10, 2025.

Compare on the AI leaderboard · All AI models

More models from DeepSeek