Baltor Get started

Endpoints

Xiaomi Token Plan (Europe)

A hosted service with its own key and prices. This page lists the addresses it answers, the facts its documentation states, and the setup of each harness.

Addresses and facts

  • OpenAI Chat Completions: https://token-plan-ams.xiaomimimo.com/v1 models.dev, read
Authentication
Authorization: Bearer, with the key in XIAOMI_API_KEY models.dev, read
Structured output
Unknown
Tool calling
5 of 9 listed models The share of this provider's models that models.dev records with tool calling. models.dev, read
Rate limits
Unknown
Prices
Unknown
Data retention
Unknown
Documentation
Read the page models.dev, read
Output limits Baltor recorded
Unknown

Harness setup

Replace mimo-v2-pro with the model you want.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "xiaomi-token-plan-ams": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Xiaomi Token Plan (Europe)",
      "options": {
        "baseURL": "https://token-plan-ams.xiaomimimo.com/v1",
        "apiKey": "{env:XIAOMI_API_KEY}"
      },
      "models": {
        "mimo-v2-pro": {
          "name": "mimo-v2-pro"
        }
      }
    }
  }
}
  • OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.

From OpenCode documentation, read .

Pi

Put this in ~/.pi/agent/models.json:

{
  "providers": {
    "xiaomi-token-plan-ams": {
      "baseUrl": "https://token-plan-ams.xiaomimimo.com/v1",
      "api": "openai-completions",
      "apiKey": "$XIAOMI_API_KEY",
      "models": [
        {
          "id": "mimo-v2-pro"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and Xiaomi Token Plan (Europe) documents no Responses address. A gateway that offers one can sit in between.

  • Codex speaks the Responses API only: responses is the one supported wire API of a custom provider. Ollama and LM Studio are built in and start with --oss.

From Codex documentation, read .

Claude Code

Claude Code sends Anthropic Messages requests, and Xiaomi Token Plan (Europe) documents no such address. A gateway that translates to that API can sit in between.

  • Claude Code sends Anthropic Messages requests to ANTHROPIC_BASE_URL. Anthropic says it does not support routing Claude Code to models other than Claude through any gateway, so some features may not work with another model.

From Claude Code documentation, read .

Models it lists

Prices in US dollars per million tokens, input and output, as models.dev, read records them.

ModelInputOutputContextAs of
MiMo-V2-Pro mimo-v2-pro0 USD0 USD1,048,576 older than 30 days
MiMo-V2-TTS mimo-v2-tts0 USD0 USD8,192 older than 30 days
MiMo-V2.5 mimo-v2.50 USD0 USD1,048,576 older than 30 days
MiMo-V2.5-Pro mimo-v2.5-pro0 USD0 USD1,048,576 older than 30 days
MiMo-V2.5-TTS mimo-v2.5-tts0 USD0 USD8,192 older than 30 days
MiMo-V2.5-TTS-VoiceClone mimo-v2.5-tts-voiceclone0 USD0 USD8,192 older than 30 days
MiMo-V2.5-TTS-VoiceDesign mimo-v2.5-tts-voicedesign0 USD0 USD8,192 older than 30 days
MiMo-V2.6-Flash mimo-v2.6-flash0 USD0 USD1,048,576
MiMo-V2.6-Pro mimo-v2.6-pro0 USD0 USD1,048,576

Sources of this page