DeepSeek V3.2
Open weightToolsDeepSeek · Released December 2025
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...
It is part of DeepSeek's open-weight line, known for delivering near-frontier reasoning and coding quality at a fraction of typical frontier pricing.
Facts and pricing
- Provider
- DeepSeek
- Context window
- 164K tokens
- Input price
- 3.0 credits / 1M tokens ($0.27 raw)
- Output price
- 4.4 credits / 1M tokens ($0.40 raw)
- Vision (image input)
- No
- Tool calling
- Yes
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.
Try DeepSeek V3.2 now
What DeepSeek V3.2 is best for
- Everyday chat and drafting on an open-weight model with transparent lineage
- Long documents: the 164K-token window holds lengthy reports, contracts or papers whole
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Example prompts
Prompts that suit a open weight model like DeepSeek V3.2:
- Draft a project update from these rough notes
- Explain how HTTPS works to a curious teenager
- Turn this list of features into a changelog entry
- Brainstorm objections to this proposal and how to answer them
DeepSeek family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| DeepSeek V4 Flash Vision Exp | 1.0M | 2.4 | 7.3 | August 2026 |
| DeepSeek V4 Pro 0813 | 1.0M | 6.4 | 19.1 | August 2026 |
| DeepSeek V4 Pro 0813 (batch) | 1.0M | 14.5 | 43.6 | August 2026 |
| DeepSeek V4 Flash 0731 | 1.0M | 0.72 | 2.0 | July 2026 |
| DeepSeek V4 Flash 0731 (batch) | 1.0M | 1.5 | 3.1 | July 2026 |
| DeepSeek V4 Pro 0423 | 1.0M | 9.1 | 18.2 | April 2026 |
| DeepSeek V4 Flash 0423 | 1.0M | 0.93 | 1.9 | April 2026 |
| DeepSeek V3.2 | 164K | 3.0 | 4.4 | December 2025 |
| DeepSeek V3.2 Exp | 164K | 3.0 | 4.5 | September 2025 |
| DeepSeek V3.1 Terminus | 131K | 3.0 | 11.0 | September 2025 |
Compare DeepSeek V3.2
Frequently asked questions
- What is DeepSeek V3.2?
- DeepSeek V3.2 is an AI model by DeepSeek. 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...
- How much does DeepSeek V3.2 cost on Zeplik?
- Input tokens cost 3.0 credits per million and output tokens 4.4 credits per million (1 credit = $0.10; the raw provider rates are $0.27 and $0.40 per million). New accounts start with free credits.
- How long can a conversation with DeepSeek V3.2 be?
- DeepSeek V3.2 has a 164K-token context window (163,840 tokens), which covers the conversation plus any documents you attach.
- Does DeepSeek V3.2 support images and tools?
- DeepSeek V3.2 is text-only and supports tool calling.
Related models
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
More you can do with DeepSeek V3.2
- 465 AI skillsReady-to-run expert methods for writing, data, code and more, each running on DeepSeek V3.2 or any model you pick.
- 997 integrationsConnect Gmail, Slack, GitHub, Notion and hundreds more so the assistant can work in your apps.
- Simple pricingPlus, Pro and Max plans with a monthly credit allowance that works across every model.