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...
Everything else
| Max output | 33K |
|---|---|
| Input / 1M | $0.25 |
| Output / 1M | $0.95 |
| Cache read / 1M | $0.13 |
| Cache write / 1M | — |
| 1M in + 1M out | $1.20 |
| Takes | text |
| Returns | text |
| Tools | yes |
| Reasoning | optional |
| Open weights | yes |
| Released | 2025-08-21 |
| Knowledge cutoff | 2025-03-31 |
| Retires | — |
| Catalog id | deepseek/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.