DeepSeek V3.2 Exp
Summary
DeepSeek V3.2 Exp is an open-weight language model from DeepSeek, released on 29 Sept 2025. It accepts text and generates text, with a 164K-token context window and up to 147K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.27 per million input tokens and $0.41 per million output tokens (OpenRouter), across 1 provider we track.
DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | DeepSeek |
|---|---|
| Release date | 29 Sept 2025 [OpenRouter] |
| Status | Generally available |
| Weights | Open weights [Hugging Face] |
| License | mit [Hugging Face] |
| Parameters | 685B [Hugging Face] |
| Context window | 164K (163,840 tokens) [OpenRouter] |
| Max output | 147K tokens [OpenRouter] |
| Knowledge cutoff | 31 Jul 2025 [OpenRouter] |
| Input | Text [OpenRouter] |
| Output | Text [OpenRouter] |
| Reasoning mode | Yes [OpenRouter] |
| Tool calling | Yes [OpenRouter] |
| Structured output | Yes [OpenRouter] |
| Hugging Face | deepseek-ai/DeepSeek-V3.2-Exp [Hugging Face] |
DeepSeek V3.2 Exp API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| OpenRouter deepseek/deepseek-v3.2-exp | $0.27 | $0.41 | – | 164K | OpenRouter, 18 Nov 2026 |
Running DeepSeek V3.2 Exp locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 416 GB | 417 GB | 419 GB |
| Q8_0 (8-bit) | 728 GB | 730 GB | 731 GB |
| FP16 / BF16 (16-bit) | 1371 GB | 1372 GB | 1374 GB |
At 4-bit with an 8K conversation, DeepSeek V3.2 Exp needs about 417 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.
Frequently asked questions
What is the context window of DeepSeek V3.2 Exp?
DeepSeek V3.2 Exp has a context window of 163,840 tokens (164K) and can generate up to 147,456 tokens in a single response, according to OpenRouter.
How much does the DeepSeek V3.2 Exp API cost?
DeepSeek V3.2 Exp is listed from $0.27 per million input tokens and $0.41 per million output tokens (OpenRouter). Prices last verified 18 Nov 2026.
Is DeepSeek V3.2 Exp open source?
DeepSeek V3.2 Exp is an open-weight model: its weights are published on Hugging Face as deepseek-ai/DeepSeek-V3.2-Exp under the mit license. Check the license terms before commercial use.
When was DeepSeek V3.2 Exp released?
DeepSeek released DeepSeek V3.2 Exp on 29 Sept 2025, according to OpenRouter.
How much VRAM does DeepSeek V3.2 Exp need?
About 417 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 730 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Qwen3 VL 30B A3B Instruct | Alibaba (Qwen) | 4 Oct 2025 | 131K | $0.15 | $0.60 | Open |
| Cydonia 24B V4.1 | Thedrummer | 27 Sept 2025 | 131K | $0.30 | $0.50 | Open |
| GPT OSS Safeguard 120B | OpenAI | 29 Oct 2025 | 128K | $0.15 | $0.60 | Open |
| Nvidia Nemotron Nano 12B V2 VL | NVIDIA | 28 Oct 2025 | 131K | $0.20 | $0.60 | Open |
| Gemma Sea Lion V4 27B It | Aisingapore | 23 Sept 2025 | 128K | $0.35 | $0.56 | Open |
| Qwen3 VL 8B Instruct | Alibaba (Qwen) | 14 Oct 2025 | 262K | $0.25 | $0.75 | Open |
Change history
No changes detected since we started tracking this model. We re-check every source daily.