DeepSeek V3.2
DeepSeek V3.2 — DeepSeek text model with an Intelligence Index of 28, a 200K-token context window and a blended price of $0.11/1M tokens (open weights).
Key specifications
| Intelligence Index | 28 |
|---|---|
| Coding Index | 44.2 |
| Agentic Index | 18.3 |
| Arena Elo | — |
| Context window (K tokens) | 200 |
| Blended price ($/1M tokens) | 0.1 |
| Output speed (tokens/s) | — |
About DeepSeek V3.2
The DeepSeek V3.2 is a text only model from DeepSeek with an Intelligence Index of 28.0, a Coding Index of 44.2 and a 200K-token context window. It runs at a blended price of $0.11 per million tokens. It is open weights, so it can also be self-hosted. Leaderboard indices are a strong signal but only part of real-world quality, which also depends on tool use, latency and task fit.
The comparisons below show how DeepSeek V3.2 stacks up against the alternatives people most often weigh against it, with the specific numbers laid out side by side.
Frequently asked questions
Is the DeepSeek V3.2 any good?
DeepSeek V3.2 — DeepSeek text model with an Intelligence Index of 28, a 200K-token context window and a blended price of $0.11/1M tokens (open weights).
What are the key specs of the DeepSeek V3.2?
See the specification table above for the full breakdown.