DeepSeek V3.1

deepseek/deepseek-chat-v3.1

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

Compare

Context window: 164K
Input: Text
Output: Text
Released: 2025-08-21

Max output: 33K
Knowledge cutoff: 2025-03-31
Model parameters: 671B
Active parameters: 37B
Weights: Open
Capabilities: Open weight, Reasoning, Structured, Temperature, Tool call

Pricing

No official pricing available.

Estimate usage cost

Compare verified public prices for this exact model and region. Enter uncached input and cache usage separately. Estimates exclude unspecified fees, credits and currency conversion. Set requests to zero to estimate token charges only.

Input tokens

Output tokens

Cache read tokens

Cache write tokens

Requests

Context tokens (optional)

Currency

Batch processing

Performance

Overall capability

44.3/100

Coding: —
Reasoning: 41.3
Professional work: —
Knowledge & language: 47.4


Humanity’s Last ExamDeepSeek V3.1 (Reasoning)	Reasoning	Artificial Analysis	2026-11-05
CritPtDeepSeek V3.1 (Reasoning)	Reasoning	Artificial Analysis	2026-11-05
IFBench（Artificial Analysis）DeepSeek V3.1 (Reasoning)	Knowledge & language	Artificial Analysis	2026-11-05
AA-LCRDeepSeek V3.1 (Reasoning)	Knowledge & language	Artificial Analysis	2026-11-05
Arena Text Overall	Blind	LMArena	2026-10-28
AA-OmniscienceDeepSeek V3.1 (Reasoning)	Knowledge & language	Artificial Analysis	2026-10-27

Providers

No providers found

ModelRegistry · Catalog updated 2026-11-05