Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
| 1 model | deepseek-aiDeepSeek-V3.2Remove × |
|---|---|
| What’s different | DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a… |
| Date | Dec 1, 2025Listed |
API prices USD · provider configuration shown below | |
| Listed rate | $0.2088 in / $0.3096 out/ 1M tokensGMICloud · via OpenRouter · all routes ↗gmicloud/fp8 · quantization=fp8 |
| Provider endpoints | 16 endpoints → |
Specifications | |
| Context window | 163.8K |
| Max output | 163.8K |
| Parameters | — |
| Tool calling | Supported |
| Structured output | Supported |
| Reasoning | Supported |
| Prompt caching | Supported |
| Open weights | Supported |