Compare
2–4 model comparison. Best-in-row is highlighted.
DeepSeek V3.1open
DeepSeek · deepseek__deepseek-chat-v3.1
DeepSeek V3.2open
DeepSeek · deepseek__deepseek-v3.2
Identity
| Field | deepseek__deepseek-chat-v3.1 | deepseek__deepseek-v3.2 |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Slug | deepseek__deepseek-chat-v3.1 | deepseek__deepseek-v3.2 |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | deepseek-ai/DeepSeek-V3.1 | deepseek-ai/DeepSeek-V3.2 |
Quality
| Field | deepseek__deepseek-chat-v3.1 | deepseek__deepseek-v3.2 |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | deepseek__deepseek-chat-v3.1 | deepseek__deepseek-v3.2 |
|---|---|---|
| Input $ / 1M tokens | $0.25 | $0.26 |
| Cached input $ / 1M | $0.13 | $0.13 |
| Output $ / 1M tokens | $0.95 | $0.38 |
Context
| Field | deepseek__deepseek-chat-v3.1 | deepseek__deepseek-v3.2 |
|---|---|---|
| Max context tokens | 163,840 | 163,840 |
| Max output tokens | 147,456 | 147,456 |
Modalities
| Field | deepseek__deepseek-chat-v3.1 | deepseek__deepseek-v3.2 |
|---|---|---|
| Input | text | text |
| Output | text | text |