Skip to main content
The original DeepSeek-V4.1-Flash-1017 checkpoint (revision 2026-10-17) on OS3’s own GPUs. Each id is always answered by exactly this revision, never by another model.
Preview, best effort: there is no uptime promise yet.

APIs

Chat completions (/v1/chat/completions), Anthropic’s Messages API (/v1/messages) and OpenAI’s Responses API (/v1/responses), streamed or not. Any other API naming these ids is refused with 400 catalog_api_unsupported. The base URL is https://gateway.os3compute.com/v1 (Messages: https://gateway.os3compute.com). It answers from the nearer of OS3’s two US locations.

Context and output

Context: 1,048,512 tokens, prompt and answer together. A prompt that does not fit is refused, never cut.
  • By default an answer is at most 8,192 tokens without thinking, 65,536 with it and 131,072 at max effort. Set max_tokens (1 to 393,216) for another cap. Thinking tokens count toward it.
  • One completion a request (n = 1).

Thinking

  • The model thinks unless you send reasoning_effort: "none" (or thinking: {"type": "disabled"}).
  • Efforts are low, high (the default) and max.
  • Thinking comes back in reasoning_content, apart from content. Its tokens are billed as output.
  • On a tool turn, send the assistant message back with its reasoning_content.
  • Messages API: a thinking block with an empty signature. Responses API: a reasoning item with reasoning_text.

Tools

  • Your own function tools, with tool choice auto, none, required or a named tool.
  • Tools a provider runs on its servers (web search, code execution, computer use and the like) are refused with 400 unsupported_tool.

Images

  • Up to 600 a request, as data URLs or public http(s) URLs.
  • Images inside a tool result work too.

Streaming and long answers

  • A stream sends : keep-alive lines while the model works (Messages: event: ping).
  • A long answer that is not streamed starts with status 200 after 10 seconds and sends a blank line every 10 seconds until its JSON is ready. The OpenAI and Anthropic SDKs read it as usual.
  • Prompts above 200,000 tokens: rarely, one takes 10 to 30 seconds longer to start answering. Set a first-token timeout of at least 120 seconds.

Responses API

OS3 keeps no response: send the whole conversation each turn. store: true, previous_response_id, conversation and background are refused with 400 unsupported_parameter.

Answers

  • model is the id you sent. system_fingerprint names the serving configuration that answered.
  • Every answer carries an x-os3-request-id header.
  • Errors have OpenAI’s shape (Anthropic’s on the Messages API). See Errors.