Xiaomi · Text

OpenClaw x MiMo

RunAPI supports text-only requests for both MiMo models through Chat Completions, Responses, and Anthropic Messages on their existing synchronous and SSE paths. The only verified image shape is base mimo-v2.5 with synchronous OpenAI Chat Completions, where messages[].content[] may contain text and remote HTTP(S) image_url parts. Pro remains text-only; other image and media shapes are closed or unverified.

2 variants from $0.11 / 1M tokens Commercial OK
Get API Key View OpenClaw Docs

Prerequisite: npx runapi mcp install

Prompt

Prompt models

Use mimo-v2.5 when it matches the task: Custom tool calling on Chat Completions and native Messages; remote images on synchronous Chat.

You have access to RunAPI chat models for MiMo.

Available MiMo models:
- mimo-v2.5: Custom tool calling on Chat Completions and native Messages; remote images on synchronous Chat
  chat endpoints: /v1/chat/completions, /v1/responses, /v1/messages
- mimo-v2.5-pro: mimo-v2.5-pro text-only; multimodal input remains unverified
  chat endpoints: /v1/messages, /v1/chat/completions, /v1/responses

Use the model ID and chat endpoint that match the user's request.
Example request: Summarize this report, identify its main points, and draft a clear response.
Verify the active model with: openclaw models status;openclaw models set runapi/<model-id>

Public Versions and Endpoints

Model ID Endpoints Price Catalog
mimo-v2.5
/v1/chat/completions /v1/responses /v1/messages
$0.11 / 1M tokens Model detail
mimo-v2.5-pro
/v1/messages /v1/chat/completions /v1/responses
$0.35 / 1M tokens Model detail

Verify

Poll until the task reaches a terminal status

Select <model-id> to generate verification commands.

Configuration

Guide endpoint: <endpoint>

Select <model-id> to generate a request with the endpoint's public input contract.
How it works

Get Started in 3 Steps

  1. Choose a model ID

    Select a public catalog model ID and review its endpoint and current starting price.

  2. Configure RunAPI

    Add the provider configuration for this agent.

  3. Verify the result

    Run the agent status and model-selection commands shown below.

What to Build with OpenClaw + MiMo

  • Agent coding and reasoning

    Let your agent plan, write, and review code or work through multi-step problems with the model's reasoning.

  • Long document analysis and extraction

    Summarize reports, contracts, or codebases and pull structured fields out of long documents.

  • Tool-calling workflows

    Connect the model to functions and APIs so your agent can look up data and take actions between replies.

Why Use MiMo Through RunAPI + OpenClaw

  • 2 variants, one API key

    Use one RunAPI connection to choose among the live model variants without changing your integration.

  • Clear usage pricing

    See current catalog pricing before you send a request, with no subscription or minimum spend required.

  • Direct responses

    Synchronous calls return the result in the same response, so your agent can use it immediately without task polling.

OpenClaw + MiMo Questions

What is the difference between MiMo 2.5 and MiMo 2.5 Pro?

Both models support text-only requests through Chat Completions, Responses, and Anthropic Messages on their existing synchronous and SSE paths. Base mimo-v2.5 additionally supports remote HTTP(S) image_url parts in messages[].content[] for synchronous OpenAI Chat Completions; mimo-v2.5-pro is text-only.

Which APIs can I use with MiMo 2.5 on RunAPI?

Text-only requests remain supported for both models through Chat Completions, Responses, and Anthropic Messages on their existing synchronous and SSE paths. For images, only base mimo-v2.5 with synchronous OpenAI Chat Completions and remote HTTP(S) image_url parts in messages[].content[] is verified.

Does MiMo 2.5 accept non-text input?

Base mimo-v2.5 accepts remote HTTP(S) image_url parts alongside text in messages[].content[] only for synchronous OpenAI Chat Completions; Pro is text-only. Image input through Responses, Anthropic Messages, streaming/SSE, data URLs, and audio, file, or video is not verified.

Which model ID should I use?

Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version.

Does this guide configure a chat model?

Yes. This Model Line supports a client-facing LLM protocol.

Start using MiMo with OpenClaw

Get API Key Read Quickstart

Building with a team?

We're here to help with enterprise setup, integrations, and technical questions.

Contact Us