> ## Documentation Index
> Fetch the complete documentation index at: https://docs.os3compute.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Differences from DeepSeek's API

> What OS3 serves differently from DeepSeek's own API.

The model is DeepSeek's checkpoint. The servers and the API in front of it are OS3's. Prompt rendering, thinking and effort names, output defaults and maximum, `temperature`, `top_p` and image allowances follow DeepSeek's API. These do not:

* Context is 1,048,512 tokens, 64 fewer than DeepSeek's window.

- `max_completion_tokens` is read as the output cap when `max_tokens` is absent (`max_tokens` wins when both are sent).
- `response_format: {"type": "json_object"}` always returns a JSON object. DeepSeek's API can return any JSON value.
- Image `detail: "low"` is accepted only up to 512 px on the longer side. A larger image is refused with a 400 (DeepSeek's API downscales it).
- Images by URL: 60 seconds an image and 600 a request, as on DeepSeek's API, but all of a request's images within 300 seconds and about 36 MiB in total, at most 3 redirects, public hosts only.
- Not offered: the Files API (`file_id`, `file_data`), web search, URL reading, the application APIs DeepSeek released on 2026-11-13, and FIM completion.
- Tool call ids, log probability fields and stream framing have DeepSeek's shapes but are made by OS3.
- A message that contains the literal text `<｜deepseek_image｜>` next to a real image is refused with a 400.
- Where the model is unsure of the next token, the text can differ from DeepSeek's API or from another host of the same checkpoint. `temperature: 0` does not give the same text every time.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.