DeepSeek V3
by DeepSeek Model family in Model APIs & inference, indexed and not reviewed
on OpenRouter
Not reviewed
No score, grade or rank. This listing is facts from OpenRouter and our own checks, and it stays out of the rankings until the panel reviews it.
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...
Facts
- Maker
- DeepSeek
- Models
- 5 on OpenRouter
- Newest
deepseek/deepseek-v3.2
Why it's listed
- OpenRouter lists it, with prices from the providers that serve it.
Being indexed says nothing about quality, and nobody can pay for it. Is this yours? Ask for a review.
Models 5
| Model | Released | Context | Input / 1M | Output / 1M | Supports |
|---|---|---|---|---|---|
DeepSeek V3.2deepseek/deepseek-v3.2 | Dec 2025 | 163k | $0.26 | $0.38 | tools, structured output, reasoning, caching |
DeepSeek V3.2 Expdeepseek/deepseek-v3.2-exp | Sep 2025 | 163k | $0.27 | $0.41 | tools, structured output, reasoning |
DeepSeek V3.1deepseek/deepseek-chat-v3.1 | Aug 2025 | 163k | $0.25 | $0.95 | tools, structured output, reasoning, caching |
DeepSeek V3 0324deepseek/deepseek-chat-v3-0324 | Mar 2025 | 163k | $0.29 | $1.14 | tools, structured output, caching |
DeepSeek V3deepseek/deepseek-chat | Dec 2024 | 163k | $0.2574 | $1.0287 | tools, structured output |
Prices and limits as OpenRouter lists them, in dollars per million tokens; a provider's own price can differ.