Baltor Get started

Models

MiniMax M1

By MiniMax. Unknown parameters, a context window of 1,000,000 tokens, licence Unknown.

Facts

Released
2025-06-17 the day OpenRouter added the model OpenRouter, read
Licence
Unknown
Open weights
Unknown
Parameters
Unknown
Active parameters
Unknown
Knowledge cutoff
2024-06-30 the knowledge cutoff OpenRouter lists OpenRouter, read
Context window
  • 1,000,000 tokens the context length OpenRouter lists OpenRouter, read
Longest output
  • 40,000 tokens the largest output OpenRouter's first provider allows OpenRouter, read
Tool calling
  • Yes OpenRouter lists tools among the supported parameters OpenRouter, read
Structured output
  • No OpenRouter lists no structured output parameter OpenRouter, read
Reasoning controls
  • Yes OpenRouter lists reasoning controls OpenRouter, read
Inputs and outputs
text in, text out OpenRouter, read
Good for
  • Reasoning: OpenRouter lists reasoning controls for it OpenRouter, read

Prices

Prices in US dollars per million tokens, as each source lists them
ProviderInputOutputContextAs ofSource
Minimax through OpenRouter0.400 USD2.20 USD1,000,000OpenRouter endpoints, read
Novita through OpenRouter0.550 USD2.20 USD1,000,000OpenRouter endpoints, read

Run it on your own hardware

No source lists weight files or a parameter count for this model, so its memory needs are Unknown.

Use it from your harness

Set up for OpenRouter with the model minimax/minimax-m1. 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": {
        "minimax/minimax-m1": {
          "name": "MiniMax M1",
          "limit": {
            "context": 1000000,
            "output": 40000
          }
        }
      }
    }
  }
}
  • 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": "minimax/minimax-m1"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

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

model = "minimax/minimax-m1"
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="minimax/minimax-m1"
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 .