RAG and data · 2026-10-21
A long-document research flow with 1M context on MiMo V2.5 Pro
How to build a research flow that analyzes a long document set in a single request with MiMo V2.5 Pro's 1 million token context window, how to add current data through your own search step, and how to move the same flow to MiMo V2.6 Pro now that the model was retired on 14 October 2026.
The model was retired on 14 October 2026
MiMo V2.5 Pro was retired on 14 October 2026; since 02:00 UTC that day, requests to `mimo/mimo-v2.5-pro` return a model_retired (HTTP 410) error. Its successor `mimo/mimo-v2.6-pro` is offered at the same price and carries the same 1M-token context window.
The usage pattern below applies unchanged to the successor; updating the model identifier in your requests to `mimo/mimo-v2.6-pro` is enough. V2.6 has thinking on by default, and while thinking is on it ignores `temperature` and `top_p`.
Using 1M context together with current data
The 1 million token context window lets you carry many long documents (a series of reports or contracts, for example) in a single request; but those documents only carry information up to a certain date. An analysis that needs current information has to close that gap.
The model-side `web_search` tool of MiMo models is not available on LLMTR right now; requests that add `web_search` to the `tools` array return an error. Collect current data on your side instead: fetch the relevant pages with your own search service or from sources you trust, and add their text to the context next to your documents, together with each source's address and date.
A practical flow is loading the document set and the current sources you collected into context, then asking the model to compare a claim in the documents against those sources and to state which source each conclusion rests on. Because you pick the sources, you also control which data enters the analysis.
- 1M context: carries many long documents in one request, but the information freezes at a certain date.
- The model-side web_search tool is not available on LLMTR right now; collect current data on your side.
- Add the sources you collect to the context together with their address and date.
- Ask the model to state which source each conclusion rests on.
Context size drives the cost
The main cost line in this flow is input tokens: every document and every current source you add to the context is billed again on each request. Adding only the documents and sources relevant to the question at hand, rather than filling the context for every question, keeps total cost predictable.
Frequently asked questions
Do my requests to MiMo V2.5 Pro automatically go to V2.6 Pro?
No, there is no automatic reroute; requests to `mimo/mimo-v2.5-pro` have returned a model_retired error since 14 October 2026. You need to update the model identifier to `mimo/mimo-v2.6-pro` yourself.
Can I use the web_search tool on MiMo V2.5 Pro?
Not on LLMTR right now; requests that include `web_search` return an error. For flows that need current information, collect the sources on your side and add them to the context as text.