DeepSeek V3.2 Speciale
DeepSeek V3.2 Speciale is DeepSeek's language model with a 164K context window, available from 2 providers, starting at $0.287 / 1M input and $0.431 / 1M output. A high-compute variant of DeepSeek V3.2 optimized for maximum reasoning and agentic performance using DeepSeek Sparse Attention for long-context tasks.
Capabilities
Input1/5
β
Β·
Β·
Β·
Β·
Output1/5
β
Β·
Β·
Β·
Β·
Capabilities6/13
β
Β·
β
Β·
β
β
Β·
Β·
Β·
Β·
Β·
β
β
Pricing by Provider
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
 OpenRouter | $0.287 | $0.431 | $0.058 |
 Azure AI Foundry | $0.580 | $1.68 | N/A |
Cost Calculator
Preset:
Compares every provider & tier in USD
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| DeepSeek V3.2 Speciale | 164K | $0.287 | $0.431 | Current | |
| DeepSeek V3.2 Thinking | 128K | $0.620 | $1.85 | Available | |
| DeepSeek V3.2 Exp Reasoning | β | β | β | β | Available |
| DeepSeek V3.2 Exp | β | β | β | β | Available |
| DeepSeek V3.1 671B | β | 164K | β | β | Available |
| DeepSeek V3 324B | β | β | β | β | Available |
| DeepSeek V3 Turbo | β | 64K | $0.400 | $1.30 | Available |
| DeepSeek V3.2 Reasoning | β | β | β | β | Available |
| DeepSeek V3.1 Terminus Reasoning | β | β | β | β | Available |
| DeepSeek V3.1 Reasoning | β | β | β | β | Available |
| DeepSeek V3 2SP | β | β | $0.580 | $1.68 | Available |