DeepSeek-V3.2 (Non-thinking)
DeepSeekOverview
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.
DeepSeek-V3.2 (Non-thinking) was released on December 1, 2025. API access is available through DeepSeek.
Performance
Timeline
Other Details
Related Models
Compare DeepSeek-V3.2 (Non-thinking) to other models by quality (GPQA score) vs cost. Higher scores and lower costs represent better value.
Performance visualization loading...
Gathering benchmark data from similar models
Benchmarks
Pricing
Pricing, performance, and capabilities for DeepSeek-V3.2 (Non-thinking) across different providers:
| Provider | Input ($/M) | Output ($/M) | Max Input | Max Output | Latency (s) | Throughput | Quantization | Input | Output |
|---|---|---|---|---|---|---|---|---|---|
 DeepSeek | $0.28 | $0.42 | 131.1K | 8.2K | 0.3 | 100.0 tok/s | — | Text Image Audio Video | Text Image Audio Video |
Example Outputs
Recent Posts
Recent Reviews
API Access
API Access Coming Soon
API access for DeepSeek-V3.2 (Non-thinking) will be available soon through our gateway.
FAQ
Common questions about DeepSeek-V3.2 (Non-thinking)