Model overview
最强开源 MoE 模型 DeepSeek-V2，全球首个在代码、数学能力上与GPT-4-Turbo争锋的模型，在代码、数学的多个榜单上位居全球第二；DeepSeek 是文科生；支持 32K 上下文
The summary below is compiled from sources by an AI model, not our own testing. Verify selection decisions against original sources and your workload.
Key features
- 支持最长163840 tokens的上下文长度
- 采用MoE（Mixture of Experts）架构
- 在代码和数学任务多个基准榜单中位列全球第二
Limitations & considerations
Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.
Source prices & cost analysis
Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.
| Source / channel | Input | Output | Billing unit | Collected at |
|---|---|---|---|---|
| OpenRouter · deepseek/deepseek-chat ↗ | USD 0.2574 | USD 1.0287 | Per million tokens | 2026/11/2 06:25:30 |
| Apilio · default ↗ | Not verified | Not verified | 渠道倍率待核验 | 2026/11/2 06:25:17 |
| Apilio · 国产特价 ↗ | Not verified | Not verified | 渠道倍率待核验 | 2026/11/2 06:25:17 |
Estimate monthly base token costs
Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.
Public benchmarks & run configuration
暂无已采集的可核验公开评分。模型未上榜不代表能力较低。
View full indexed rankings →Frequently asked questions
DeepSeek V3 是否开源？
资料中未提及 DeepSeek V3 的开源状态，仅称 DeepSeek-V2 为‘最强开源 MoE 模型’；V3 的许可或开源属性未说明。
DeepSeek V3 在哪些能力上与 GPT-4-Turbo 相当？
资料指出其在代码、数学能力上‘与GPT-4-Turbo争锋’，并在相关榜单位居全球第二。
模型是否支持结构化输出和工具调用？
是的，标签明确包含 'structured_outputs' 和 'tools'，表明支持结构化输出与工具调用功能。
Do open weights permit free commercial use?
Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.
Are these real-time billing prices?
These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.
Sources & traceability
许可证：来源未披露，须进一步核验。模型介绍与第三方评测均以原来源的具体版本和方法为准。