DeepSeek

DeepSeek-V3.1

Generally availableOpen weights164K contextReasoning

Summary

DeepSeek-V3.1 is an open-weight language model from DeepSeek, released on 21 Aug 2025. It accepts text and generates text, with a 164K-token context window and up to 128K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.25 per million input tokens and $0.95 per million output tokens (DeepInfra), across 4 providers we track.

DeepSeek chat model for instruction following, coding, and analysis

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperDeepSeek
Release date21 Aug 2025 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [models.dev]
Context window164K (163,840 tokens) [models.dev]
Max output128K tokens [models.dev]
Knowledge cutoffAug 2025 [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]

DeepSeek-V3.1 API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
DeepInfra
deepseek-ai/DeepSeek-V3.1
$0.25$0.95$0.13164Kmodels.dev, 18 Nov 2026
Vercel AI Gateway
deepseek/deepseek-v3.1
$0.25$0.95$0.13164Kmodels.dev, 18 Nov 2026
Hugging Face Inference Providers
deepseek-ai/DeepSeek-V3.1
$0.27$1–131Kmodels.dev, 18 Nov 2026
SiliconFlow
deepseek-ai/DeepSeek-V3.1
$0.27$1–164Kmodels.dev, 18 Nov 2026

Frequently asked questions

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

DeepSeek-V3.1 has a context window of 163,840 tokens (164K) and can generate up to 128,000 tokens in a single response, according to models.dev.

How much does the DeepSeek-V3.1 API cost?

DeepSeek-V3.1 is listed from $0.25 per million input tokens and $0.95 per million output tokens (DeepInfra). Prices last verified 18 Nov 2026.

Is DeepSeek-V3.1 open source?

DeepSeek-V3.1 is an open-weight model. Check the license terms before commercial use.

When was DeepSeek-V3.1 released?

DeepSeek released DeepSeek-V3.1 on 21 Aug 2025, according to models.dev.

Which providers offer DeepSeek-V3.1?

We track DeepSeek-V3.1 on 4 providers: DeepInfra, Vercel AI Gateway, Hugging Face Inference Providers, SiliconFlow.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
GLM-4.5-AirZhipu AI (Z.ai)28 Jul 2025131K$0.13$0.85Open
UncensoredCognitivecomputations9 Jul 2025128K$0.20$0.90Open
Gemma Sea Lion V4 27B ItAisingapore23 Sept 2025128K$0.35$0.56Open
Qwen3 VL 235B A22B InstructAlibaba (Qwen)23 Sept 2025262K$0.20$0.88Open
Cydonia 24B V4.1Thedrummer27 Sept 2025131K$0.30$0.50Open
Magistral Small 1.2Mistral AI18 Sept 2025128K$0.50$1.50Open

Change history

  • Context window changed from 131K to 164K
  • Max output changed from 8K to 128K
  • Context window changed from 164K to 131K
  • Context window changed from 164K to 164K
  • Name changed from deepseek-ai/DeepSeek-V3.1 to DeepSeek-V3.1
  • Max output changed from 164K to 8K
  • Max output changed from 8K to 164K
  • Context window changed from 131K to 164K
  • Name changed from DeepSeek-V3.1 to deepseek-ai/DeepSeek-V3.1
  • Max output changed from 128K to 8K
  • Context window changed from 164K to 131K
  • Max output changed from 8K to 128K
  • Max output changed from 128K to 8K
  • Max output changed from 8K to 128K
  • Max output changed from 164K to 8K
  • Context window changed from 164K to 164K
  • Name changed from deepseek-ai/DeepSeek-V3.1 to DeepSeek-V3.1
  • Name changed from DeepSeek-V3.1 to deepseek-ai/DeepSeek-V3.1
  • Context window changed from 131K to 164K
  • Max output changed from 8K to 164K
  • Context window changed from 164K to 131K
  • Name changed from deepseek-ai/DeepSeek-V3.1 to DeepSeek-V3.1
  • Context window changed from 164K to 164K
  • Max output changed from 164K to 8K
  • Name changed from DeepSeek-V3.1 to deepseek-ai/DeepSeek-V3.1

Sources