/ Models

Language models

DeepSeek: DeepSeek 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...

Maker
Deepseek
Context window
164K
Max output
33K
Input / 1M
$0.25
Output / 1M
$0.95
1M in + 1M out
$1.20

Everything else

Max output33K
Input / 1M$0.25
Output / 1M$0.95
Cache read / 1M$0.13
Cache write / 1M
1M in + 1M out$1.20
Takestext
Returnstext
Toolsyes
Reasoningoptional
Open weightsyes
Released2025-08-21
Knowledge cutoff2025-03-31
Retires
Catalog iddeepseek/deepseek-chat-v3.1

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models