Claude - CowAgent

Claude is provided by Anthropic and supports both text chat and image understanding. The mainstream Sonnet / Opus models natively support vision, so no separate Vision model needs to be specified.

All capabilities below can be configured in one place via the “Model Management” page in the Web Console, with no need to manually edit the configuration file.

Text Chat

{
  "model": "claude-sonnet-5",
  "claude_api_key": "YOUR_API_KEY"
}

Parameter	Description
`model`	Supports `claude-sonnet-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-sonnet-4-6`, `claude-opus-4-6`, `claude-sonnet-4-5`, `claude-sonnet-4-0`, `claude-3-5-sonnet-latest`, etc. See official models
`claude_api_key`	Create one in the Claude Console
`claude_api_base`	Optional, defaults to `https://api.anthropic.com/v1`. Can be changed to a third-party proxy

Model Selection

Model	Use Case
`claude-sonnet-5`	Latest flagship; default recommendation, best balance of reasoning quality and cost
`claude-opus-4-8`	Previous flagship with the strongest reasoning, at a higher price
`claude-opus-4-7`	Earlier Opus flagship
`claude-sonnet-4-6`	Balanced cost and speed, lower cost
`claude-opus-4-6` / `claude-sonnet-4-5` / `claude-sonnet-4-0`	Earlier flagships at a lower price

Image Understanding

Once claude_api_key is configured, the Agent’s Vision tool automatically uses the Claude main model to recognize images, with no extra setup required. To manually specify a Vision model, set it explicitly in the configuration file:

{
  "tools": {
    "vision": {
      "model": "claude-sonnet-5"
    }
  }
}

​Text Chat

​Model Selection

​Image Understanding

Text Chat

Model Selection

Image Understanding