Configure Kimi (Moonshot) in CowAgent: chat with native image understanding; once moonshot_api_key is set the vision tool uses Kimi automatically. Set up from the web console.
Kimi is provided by Moonshot and supports both text chat and image understanding. The kimi-k3.1-pro, kimi-k3 and kimi-k2.x series natively support vision.
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.
kimi-k3.1-pro is the default recommendation with a 1M-token context window; kimi-k3.1-pro-highspeed offers the same intelligence at roughly 2-3x the output speed. The K3 / K3.1 series always think; tune the depth with reasoning_effort: low / high / max (default max).
Image Understanding
Once moonshot_api_key is configured, the Agent’s Vision tool automatically uses kimi-k2.6 to recognize images, with no extra setup required.To manually specify a Vision model: