DeepSeek V3.2 Exp
DeepSeek V3.2 Exp is DeepSeek's language model with a 164K context window and up to 66K output tokens, available from 3 providers, starting at $0.270 / 1M input and $0.410 / 1M output. An experimental LLM checkpoint from DeepSeek introducing DeepSeek Sparse Attention (DSA) for efficient long-context processing, positioned between V3.1 and future architectures.
DeepSeek's language model with a 164K context window and up to 66K output tokens, available from 3 providers, starting at $0.270 / 1M input and $0.410 / 1M output. An experimental LLM checkpoint from DeepSeek introducing DeepSeek Sparse Attention (DSA) for efficient long-context processing, positioned between V3.1 and future architectures.Capabilities
Input1/5
✓
·
·
·
·
Output1/5
✓
·
·
·
·
Capabilities6/13
✓
·
✓
✓
✓
·
·
·
·
·
·
✓
✓
Pricing by Provider
| Provider | Standard | Batch | ||
|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
 Novita | $0.270 | $0.410 | — | — |
 OpenRouter | $0.270 | $0.410 | — | — |
 Alibaba Qwen | $0.287 | $0.431 | $0.143 | $0.215 |
Cost Calculator
Preset:
Compares every provider & tier in USD
Other models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| DeepSeek V3.2 | — | 164K | $0.259 | $0.400 | |
| DeepSeek V3.2 Speciale | — | 164K | $0.400 | $1.20 | |
| DeepSeek V3.2 Thinking | — | 128K | $0.280 | $0.420 | |
| DeepSeek V3.2 Exp | — | — | — | — | — |
| DeepSeek V3.2 Exp | — | — | — | — | — |
| DeepSeek V3.1 Nex N1 | — | 131K | — | — | |
| DeepSeek V3.1 Terminus | Terminus | 164K | $0.210 | $0.790 | |
| DeepSeek V3.1 | — | 164K | $0.150 | $0.750 | |
| DeepSeek V3.1 671B | — | — | 164K | — | — |
| DeepSeek V3 | — | 164K | $0.200 | $0.200 |