Run Claude Code with open models such as GLM-5.3-Flash. Point it at the Anthropic-compatible endpoint of Munito AI with your key and the model names.
Claude Code runs with open models on Munito AI, because Munito AI serves an Anthropic-compatible endpoint. Create an API key, then set these variables before you start Claude Code.
export ANTHROPIC_AUTH_TOKEN=munitoai_...
export ANTHROPIC_BASE_URL=https://api.munito.ai/inference
export ANTHROPIC_MODEL='zai-org/glm-5.3-flash[1m]'
export ANTHROPIC_DEFAULT_OPUS_MODEL='zai-org/glm-5.3-flash[1m]'
export ANTHROPIC_DEFAULT_SONNET_MODEL='zai-org/glm-5.3-flash[1m]'
export ANTHROPIC_DEFAULT_HAIKU_MODEL=qwen/qwen3.8-27b
claudeANTHROPIC_AUTH_TOKEN supplies the Bearer token without a separate key approval prompt.
If an existing Claude account session interferes, run /logout and start Claude Code again.
ANTHROPIC_MODEL selects the main model.
ANTHROPIC_DEFAULT_HAIKU_MODEL selects the small model for background requests.
The Opus and Sonnet variables map those aliases to the main model, for /model and for subagents.
The [1m] suffix tells Claude Code that GLM-5.3 Flash has a context window of one million tokens.
Claude Code removes the suffix before it sends a request.
Without the suffix, Claude Code assumes 200,000 tokens for a model that it does not know, and compacts the conversation early.
GLM-5.3 Flash always reasons, also when thinking is off in Claude Code.
The effort level of Claude Code sets how much it reasons: low, high or max.
Munito AI moves any other level to the nearest of these, and to the lower one on a tie.
The base URL excludes /v1 because the Anthropic client adds it.
To keep processing in the EU or the US, use a regional host in place of api.munito.ai.
See the Messages reference for the request contract.