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
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities6/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill✓
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:
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 | — | — | — | — | Available |
| DeepSeek V3.2 Exp | — | — | — | — | Available |
| DeepSeek V3.1 671B | — | 164K | — | — | Available |
| DeepSeek V3 324B | — | — | — | — | Available |
| DeepSeek V3 Turbo | — | 64K | $0.400 | $1.30 | Available |
| DeepSeek V3.2 Reasoning | — | — | — | — | Available |
| DeepSeek V3.1 Terminus Reasoning | — | — | — | — | Available |
| DeepSeek V3.1 Reasoning | — | — | — | — | Available |
| DeepSeek V3 2SP | — | — | $0.580 | $1.68 | Available |