DeepSeek V3.1

deepseek/deepseek-chat-v3.1

DeepSeek V3.1 is a text-only model from DeepSeek with a context length of 163,840 tokens. It supports tool usage and reasoning, offers open weights, and is priced at $0.25 per million input tokens and $0.95 per million output tokens. The model was released on August 21 2025.

  • tool use
  • structured outputs
  • reasoning
  • open-weight

At a glance

providerdeepseek
releasedAug 21, 2025
context164K
input / M$0.25

Specifications

What the API gives you

Context window
164K tokens
Max output
33K tokens
Input price
$0.25 / 1M tokens
Output price
$0.95 / 1M tokens
Cache read
$0.13 / 1M tokens
Modalities
text → text
Knowledge cutoff
Mar 31, 2025
Released
Aug 21, 2025

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. This means the available task-specific evidence did not support a ranking yet—not that the model was reviewed and rejected.

Measured evidence

Public benchmark record

LMArena Text
1419 Elo2026-07-16

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open.

Open-weight model on Hugging Face.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.