> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.empiriolabs.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server.

# DeepSeek

> 5 DeepSeek models on EmpirioLabs, callable through one OpenAI-compatible API with shared billing and logs.

![DeepSeek](/_fern-files/_img/a05a934183279c322fb4dc481813f43550c9d0660f92a696d8a672cc55fc43ec.webp)

## DeepSeek

## Models from DeepSeek

![DeepSeek V4.1 Flash 1017](https://media.empiriolabs.ai/model-logos/deepseek.png)

[DeepSeek V4.1 Flash 1017](/models/deepseek-v4-1-flash-1017)

Post-trained 1017 release with stronger coding and agent results, faster task completion, shorter outputs, image input, and a 1M context window.

![DeepSeek V4 Flash 0731](https://media.empiriolabs.ai/model-logos/deepseek.png)

[DeepSeek V4 Flash 0731](/models/deepseek-v4-flash-0731)

Post-trained 0731 release with major gains across coding, repository work, tool use, and full-stack tasks, plus a 1M context window.

![DeepSeek V4 Pro 0813](https://media.empiriolabs.ai/model-logos/deepseek.png)

[DeepSeek V4 Pro 0813](/models/deepseek-v4-pro-0813)

Official 0813 Pro release with major gains across coding, repository work, tool use, and agent tasks, plus hybrid thinking and a 1M context window.

![DeepSeek V4 Pro](https://media.empiriolabs.ai/model-logos/deepseek.png)

[DeepSeek V4 Pro](/models/deepseek-v4-pro)

Flagship MoE LLM with 1.6T total / 49B active parameters and native 1M context for advanced math, logical inference, and specialized coding.

![Janus-Pro DeepSeek](https://media.empiriolabs.ai/model-logos/janus-pro-deepseek.png)

[Janus-Pro DeepSeek](/models/janus-pro-deepseek)

Autoregressive framework on the Janus Pro 7B model that unifies multimodal understanding and image generation in one architecture.