Integrations
Claude Code
Use BlazeInfer models in Claude Code through the LiteLLM proxy.
SupportedTested with: Through LiteLLM 1.108.4
Claude Code is Anthropic's coding agent for the terminal. Use it with BlazeInfer models through LiteLLM: set up the LiteLLM proxy with your BlazeInfer models, then point Claude Code at the proxy.
Prerequisites
- The LiteLLM proxy running with your BlazeInfer models, as in the
LiteLLM guide. This page assumes it runs on
http://localhost:4000with a model nameddeepseek-v4.1-flash. - Your LiteLLM key: the proxy's
master_keyor a virtual key. If the proxy has nomaster_key, any value works. YourBLAZE_API_KEYstays on the proxy.
Point Claude Code at the proxy
Set these environment variables, then start Claude Code:
export ANTHROPIC_BASE_URL="http://localhost:4000"
export ANTHROPIC_AUTH_TOKEN="sk-your-litellm-key"
export ANTHROPIC_MODEL="deepseek-v4.1-flash"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="deepseek-v4.1-flash"
claudeANTHROPIC_AUTH_TOKENis sent asAuthorization: Bearer. Use it instead ofANTHROPIC_API_KEY.ANTHROPIC_MODELandANTHROPIC_DEFAULT_HAIKU_MODELaremodel_namevalues from your LiteLLM config. Claude Code uses the Haiku model for background tasks, so point it at the proxy too.
To keep the settings for every session, put them under env in
~/.claude/settings.json:
{
"env": {
"ANTHROPIC_BASE_URL": "http://localhost:4000",
"ANTHROPIC_AUTH_TOKEN": "sk-your-litellm-key",
"ANTHROPIC_MODEL": "deepseek-v4.1-flash",
"ANTHROPIC_DEFAULT_HAIKU_MODEL": "deepseek-v4.1-flash"
}
}Choose a model with a large context window; coding agents send long prompts.