DeepSeek-V3.2 (Thinking)
Overview
DeepSeek-V3.2 in thinking mode. A powerful reasoning model with 685B parameters using DeepSeek Sparse Attention (DSA). This mode enables extended chain-of-thought reasoning for complex problem-solving tasks. Supports JSON output and tool calls.
DeepSeek-V3.2 (Thinking) was released on December 1, 2025. API access is available through DeepSeek.
Performance
Timeline
ReleasedUnknown
Knowledge CutoffUnknown
Specifications
Parameters
685.0B
License
MIT
Training Data
Unknown
Benchmarks
DeepSeek-V3.2 (Thinking) Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Mon Jan 19 2026Notice missing or incorrect data?Start an Issue discussion→
Pricing
Pricing, performance, and capabilities for DeepSeek-V3.2 (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 | 65.5K | 0.5 | 50.0 c/s | — | Text Image Audio Video | Text Image Audio Video |
API Access
API Access Coming Soon
API access for DeepSeek-V3.2 (Thinking) will be available soon through our gateway.
Recent Posts
Recent Reviews
FAQ
Common questions about DeepSeek-V3.2 (Thinking)
DeepSeek-V3.2 (Thinking) was released on December 1, 2025.
DeepSeek-V3.2 (Thinking) has 685.0 billion parameters.