deepseek-v3.2
DeepSeek-V3.2: Official successor to V3.2-Exp.
| Provider | Source | Input Price ($/1M) | Output Price ($/1M) | Description | Free |
|---|---|---|---|---|---|
| vercel | vercel | Input: $0.27 | Output: $0.40 | DeepSeek-V3.2: Official successor to V3.2-Exp. | |
| poe | poe | Input: - | Output: - | We introduce DeepSeek-V3.2, a next-generation foundation model designed to unify high computational efficiency with state-of-the-art reasoning and agentic performance. DeepSeek-V3.2 is built upon three core technical breakthroughs: • DeepSeek Sparse Attention (DSA): A new highly efficient attention mechanism that significantly reduces computational overhead while preserving model quality, purpose-built for long-context reasoning and high-throughput workloads. • Scalable Reinforcement Learning Framework: DeepSeek-V3.2 leverages a robust RL training protocol and expanded post-training compute to reach GPT-5-level performance. Its high-compute variant, DeepSeek-V3.2-Speciale, surpasses GPT-5 and demonstrates reasoning capabilities comparable to Gemini-3.0-Pro. • Large-Scale Agentic Task Synthesis Pipeline: To enable reliable tool-use and multi-step decision-making, we develop a novel agentic data synthesis pipeline that generates high-quality interactive reasoning tasks at scale, greatly enhancing the model’s File Support: Text, Markdown and PDF files Context window: 164k tokens | |
| venice | models-dev | Input: $0.40 | Output: $1.00 | Provider: Venice AI, Context: 163840, Output Limit: 40960 | |
| azure | models-dev | Input: $0.28 | Output: $0.42 | Provider: Azure, Context: 128000, Output Limit: 128000 | |
| baseten | models-dev | Input: $0.30 | Output: $0.45 | Provider: Baseten, Context: 163800, Output Limit: 131100 | |
| helicone | models-dev | Input: $0.27 | Output: $0.41 | Provider: Helicone, Context: 163840, Output Limit: 65536 | |
| zenmux | models-dev | Input: $0.28 | Output: $0.43 | Provider: ZenMux, Context: 128000, Output Limit: 64000 | |
| iflowcn | models-dev | Input: $0.00 | Output: $0.00 | Provider: iFlow, Context: 128000, Output Limit: 64000 | |
| synthetic | models-dev | Input: $0.27 | Output: $0.40 | Provider: Synthetic, Context: 162816, Output Limit: 8000 | |
| aihubmix | models-dev | Input: $0.30 | Output: $0.45 | Provider: AIHubMix, Context: 131000, Output Limit: 64000 | |
| azurecognitiveservices | models-dev | Input: $0.28 | Output: $0.42 | Provider: Azure Cognitive Services, Context: 128000, Output Limit: 128000 | |
| azureai | litellm | Input: $0.58 | Output: $1.68 | Source: azure_ai, Context: 163840 | |
| deepseek | litellm | Input: $0.28 | Output: $0.40 | Source: deepseek, Context: 163840 | |
| openrouter | openrouter | Input: $0.25 | Output: $0.38 | DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config) Context: 163840 |