DeepSeek-V3.2 (Non-thinking)
DeepSeek-V3.2 in non-thinking mode. A powerful language model with 685B parameters using DeepSeek Sparse Attention (DSA) for efficient long-context processing. Supports JSON output, tool calls, and chat prefix completion. This is the standard chat mode without extended reasoning.
| Provider | Status | Input | Output | Limits | Uptime | Speed | Notes |
|---|---|---|---|---|---|---|---|
| StreamLake | available | $0.20/Mtok | $0.80/Mtok | 128K tokens context | 99.8% | 1,180 ms p50 TTFT | |
| DeepInfra | available | $0.32/Mtok | $0.89/Mtok | 164K tokens context | 99.4% | 429 ms p50 TTFT | fp4 |
| Novita | available | $0.40/Mtok | $1.30/Mtok | 64K tokens context | 99.8% | 1,289 ms p50 TTFT | fp8 |