Xiaomi MiMo 2.6 Agent Model Guide: Pricing, Claude Code, and OpenCode

Xiaomi launched the MiMo-V2.6 family on September 22, 2026. The current mimo-v2.6-pro and mimo-v2.6-flash endpoints both provide 1M context, up to 128K output, and text, image, video, and audio input.

The API platform supports OpenAI-compatible and Anthropic-compatible protocols. MiMo-V2.6 keeps V2.5’s low token rates, while the V2.5 endpoints are scheduled to retire on October 21, 2026.

Official sources: MiMo model platform, MiMo pay-as-you-go pricing, MiMo Claude Code setup, and MiMo OpenCode setup.

The May V2.5 price cut remains the basis for V2.6 pricing. Cache writes are free for a limited time, and eligible Batch requests cost half the real-time cache-miss input and output rates.

Model Lineup

Model	Role	Context	Max Output	Best For
mimo-v2.6-pro	Full-modal flagship	1M	128K	Long-horizon coding, autonomous agents
mimo-v2.6-flash	Low-cost full-modal model	1M	128K	High-throughput text, image, video, and audio work
V2.5 endpoints	Previous generation	1M	128K	Migrate before October 21, 2026

API Pricing

Overseas API prices per 1M tokens:

Model	Cache-Miss Input	Cached Input	Output	Long Context Above 256K
mimo-v2.6-pro	$0.435	$0.0036	$0.87	No separate 256K-1M tier
mimo-v2.6-flash	$0.14	$0.0028	$0.28	No separate 256K-1M tier

Domestic API prices per 1M tokens:

Model	Cache-Miss Input	Cached Input	Output	Long Context Above 256K
mimo-v2.6-pro	¥3.00	¥0.025	¥6.00	No separate 256K-1M tier
mimo-v2.6-flash	¥1.00	¥0.02	¥2.00	No separate 256K-1M tier

Cache writing is currently free for a limited time. Web search is billed separately at $5 per 1,000 overseas calls or ¥16 per 1,000 domestic calls. The Token Plan billing system was also adjusted in the same announcement, with Xiaomi saying usable volume increased to roughly 5-8x depending on plan and scenario. Treat plan quotas as control-panel data and recheck before purchase.

MiMo-V2.6-Pro-UltraSpeed

UltraSpeed provides Pro capability, 1M context, and up to 128K output. Xiaomi reports up to 20x output speed. Overseas input/cache-read/output rates are $4.35/$0.036/$8.70 per million tokens; domestic rates are ¥30/¥0.25/¥60. Token rates are 10x Pro, and Batch is unsupported. See the official UltraSpeed model page.

Base URLs

Pay-as-you-go API:

OpenAI compatible:    https://api.xiaomimimo.com/v1
Anthropic compatible: https://api.xiaomimimo.com/anthropic

Token Plan, China region:

OpenAI compatible:    https://token-plan-cn.xiaomimimo.com/v1
Anthropic compatible: https://token-plan-cn.xiaomimimo.com/anthropic

Token Plan also exposes Singapore and Europe endpoints from the subscription console.

Claude Code Setup

For Claude Code, use the Anthropic-compatible endpoint:

{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.xiaomimimo.com/anthropic",
    "ANTHROPIC_AUTH_TOKEN": "your-mimo-api-key",
    "ANTHROPIC_MODEL": "mimo-v2.6-pro",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "mimo-v2.6-pro",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "mimo-v2.6-pro",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "mimo-v2.6-pro"
  }
}

For Token Plan, replace the base URL with your subscription endpoint and use the tp-xxxxx key from the subscription page.

OpenCode Setup

For OpenCode, create or edit ~/.config/opencode/opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "mimo": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "MiMo",
      "options": {
        "baseURL": "https://api.xiaomimimo.com/v1",
        "apiKey": "your-mimo-api-key"
      },
      "models": {
        "mimo-v2.6-pro": {
          "name": "mimo-v2.6-pro",
          "limit": { "context": 1048576, "output": 131072 },
          "modalities": { "input": ["text"], "output": ["text"] }
        }
      }
    }
  }
}

For image understanding, add image to the input modalities; both MiMo-V2.6 tiers are full-modal.

When to Try MiMo

Scenario	Recommendation
You need a high-capability 1M-context agent	Test mimo-v2.6-pro
You need low-cost multimodal perception	Test mimo-v2.6-flash
You are still using V2.5	Migrate before October 21
You need mature global enterprise API operations	Compare against OpenAI, Anthropic, and Google first

Related:

• DeepSeek API Pricing 2026
• DeepSeek V4 Agent Setup
• AI API Pricing Comparison 2026