Baltor Get started

Models

MiMo-V2.6-Flash

By Xiaomi. 310.8 billion parameters, a context window of 1,048,576 tokens and the licence mit.

Facts

Released
2026-09-21 the day the repository was first published on Hugging Face Hugging Face, read
Licence
mit the licence the model card declares Hugging Face, read
Open weights
Yes the weights are published in this Hugging Face repository Hugging Face, read
Parameters
310.8 billion counted from the safetensors weight files Hugging Face, read
Active parameters
11.2 billion estimate estimated from the expert counts and sizes in the configuration model configuration, read
Knowledge cutoff
Unknown
Context window
  • 1,048,576 tokens the maximum position embeddings in the model configuration model configuration, read
  • 1,048,576 tokens the context length OpenRouter lists OpenRouter, read
Longest output
  • 131,072 tokens the largest output OpenRouter's first provider allows OpenRouter, read
Tool calling
  • Yes the chat template in the tokenizer configuration accepts tool definitions Hugging Face, read
  • Yes OpenRouter lists tools among the supported parameters OpenRouter, read
Structured output
  • Yes OpenRouter lists structured outputs among the supported parameters OpenRouter, read
Reasoning controls
  • Yes OpenRouter lists reasoning controls OpenRouter, read
Inputs and outputs
text in, text out Hugging Face, read
Good for
  • Reasoning: OpenRouter lists reasoning controls for it OpenRouter, read
  • Vision: OpenRouter lists images among its inputs OpenRouter, read

Prices

Prices in US dollars per million tokens, as each source lists them
ProviderInputOutputContextAs ofSource
DeepInfra through OpenRouter0.140 USD0.280 USD1,048,576OpenRouter endpoints, read
Xiaomi through OpenRouter0.140 USD0.280 USD1,048,576OpenRouter endpoints, read

Run it on your own hardware

Weights are the sizes of the files a source lists, or an estimate from the parameter count where none does. Memory is an estimate: weights plus KV cache plus 512 MiB and 5 percent of the weights for runtime buffers. Check it against your hardware.

QuantizationWeightsMemory at 8,192 tokensMemory at 32,768 tokens
F16 estimate579 GiB609 GiB613 GiB
Q8_0 estimate308 GiB325 GiB328 GiB
Q4_0 estimate163 GiB173 GiB176 GiB

Start it with a local runtime

  • vLLM
    vllm serve XiaomiMiMo/MiMo-V2.6-Flash-RL
  • SGLang
    sglang serve --model-path XiaomiMiMo/MiMo-V2.6-Flash-RL --port 30000

Use it from your harness

Set up for OpenRouter with the model xiaomi/mimo-v2.6-flash. Each endpoint page has the same setup for its own address.

OpenCode

Put this in opencode.json in your project folder:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "openrouter": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "OpenRouter",
      "options": {
        "baseURL": "https://openrouter.ai/api/v1",
        "apiKey": "{env:OPENROUTER_API_KEY}"
      },
      "models": {
        "xiaomi/mimo-v2.6-flash": {
          "name": "MiMo-V2.6-Flash",
          "limit": {
            "context": 1048576,
            "output": 131072
          }
        }
      }
    }
  }
}
  • 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": {
    "openrouter": {
      "baseUrl": "https://openrouter.ai/api/v1",
      "api": "openai-completions",
      "apiKey": "$OPENROUTER_API_KEY",
      "models": [
        {
          "id": "xiaomi/mimo-v2.6-flash"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Put this in ~/.codex/config.toml:

model = "xiaomi/mimo-v2.6-flash"
model_provider = "openrouter"

[model_providers.openrouter]
name = "OpenRouter"
base_url = "https://openrouter.ai/api/v1"
env_key = "OPENROUTER_API_KEY"
  • 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

Put this in ~/.claude/settings.json, or variables in your shell:

export ANTHROPIC_BASE_URL="https://openrouter.ai/api"
export ANTHROPIC_AUTH_TOKEN="$OPENROUTER_API_KEY"
export ANTHROPIC_MODEL="xiaomi/mimo-v2.6-flash"
claude
  • 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 .

Published results

These are results other people published. Baltor did not run them and does not rank models by them.