DeepSeek-V3.2-Speciale: API Pricing, Context Window & Benchmarks
DeepSeek-V3.2-Speciale is a language model from DeepSeek, released in December 2025.
DeepSeek-V3.2-Speciale is a specialized variant of DeepSeek-V3.2, optimized for enhanced performance on specific tasks.
DeepSeek-V3.2-Speciale benchmarks
Rankings
Quality Tracker
DeepSeek-V3.2-Speciale Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Tue Jul 21 2026DeepSeek-V3.2-Speciale pricing
Providers
DeepSeek-V3.2-Speciale starts at $0.280 per million input tokens and $0.420 per million output tokens via DeepSeek.
| Provider | Input $/M | Output $/M | Context in / out | TTFT p50 / p95 s | Output avg / p5 c/s | Success 7d | Modalities in / out |
|---|---|---|---|---|---|---|---|
 DeepSeek | $0.280 | $0.420 | 131.1K/131.1K | —/1.00 | 30/— | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.
DeepSeek-V3.2-Speciale model size
DeepSeek-V3.2-Speciale has 685 billion parameters. See how it compares to other models in the same parameter range.
DeepSeek-V3.2-Speciale context window
Input and output token limits for DeepSeek-V3.2-Speciale, plus how it ranks on long-context understanding.
DeepSeek-V3.2-Speciale API
Available from the model provider
DeepSeek-V3.2-Speciale has an official provider API. It is not currently routed through the LLM Stats gateway.
Read the official API documentationDeepSeek-V3.2-Speciale latency
DeepSeek-V3.2-Speciale time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
DeepSeek-V3.2-Speciale examples
Recent arena outputs from DeepSeek-V3.2-Speciale, picked from the highest-ranked matchups.
DeepSeek-V3.2-Speciale license
DeepSeek-V3.2-Speciale is released under the MIT license, which permits commercial use, has 685.0B parameters.
- License
- MIT
- Commercial use allowed
- Parameters
- 685.0B
MIT License - allows commercial use
DeepSeek-V3.2-Speciale resources
Official sources for DeepSeek-V3.2-Speciale: api documentation, official playground.
DeepSeek-V3.2-Speciale vs other models
The most-compared alternatives to DeepSeek-V3.2-Speciale are MiMo-V2.5-Pro, GPT-5.2, MAI-Thinking-1. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like DeepSeek-V3.2-Speciale
Models ranked just above and below DeepSeek-V3.2-Speciale by LLM Stats score.
FAQ
Common questions about DeepSeek-V3.2-Speciale.