Meta: Llama 4 Maverick in Claude Code
Run meta-llama/llama-4-maverick as the model behind Claude Code through Redline, with a hard spend cap on the key and no prompt retention.
Llama 4 Maverick brings a very large context and mixture-of-experts efficiency. A good pick when the task is reading a lot rather than deep reasoning.
| Model id | meta-llama/llama-4-maverick |
|---|---|
| Context | 1M tokens |
| Input price | $0.216 / million tokens |
| Output price | $0.750 / million tokens |
| Tool calling | Supported |
Set it up
Point Claude Code's base URL at Redline (no /v1), set the auth token to your key, name this model, and set the context length to its real value of 1,048,576:
# Put these in your shell profile, then run: claude
export ANTHROPIC_BASE_URL=https://redline-gateway.pages.dev
export ANTHROPIC_AUTH_TOKEN=rl-...
export ANTHROPIC_MODEL=meta-llama/llama-4-maverick
export ANTHROPIC_DEFAULT_HAIKU_MODEL=qwen/qwen3-30b-a3b-instruct-2507
export CLAUDE_CODE_MAX_CONTEXT_TOKENS=1048576
Or put the same values under env in ~/.claude/settings.json:
// ~/.claude/settings.json
{
"env": {
"ANTHROPIC_BASE_URL": "https://redline-gateway.pages.dev",
"ANTHROPIC_AUTH_TOKEN": "rl-...",
"ANTHROPIC_MODEL": "meta-llama/llama-4-maverick",
"ANTHROPIC_DEFAULT_HAIKU_MODEL": "qwen/qwen3-30b-a3b-instruct-2507",
"CLAUDE_CODE_MAX_CONTEXT_TOKENS": "1048576"
}
}
ANTHROPIC_DEFAULT_HAIKU_MODEL is the cheap background model, set to qwen/qwen3-30b-a3b-instruct-2507 above. CLAUDE_CODE_MAX_CONTEXT_TOKENS is set because Claude Code assumes 200K for an id it does not recognise. Use ANTHROPIC_AUTH_TOKEN and leave ANTHROPIC_API_KEY unset. Full setup and every caveat is in the Claude Code guide.
FAQ
Can Meta: Llama 4 Maverick edit files and run commands in Claude Code?
Yes. It supports tool calling, which is what Claude Code needs to use its Read, Edit, Write and Bash tools. A model without tool calling could only chat.
How much does it cost?
$0.216 per million input tokens and $0.750 per million output tokens through Redline, margin already included. Put a spend cap on the key so an agent loop cannot overrun it.
Is this an official Anthropic setup?
No. Anthropic does not officially support routing Claude Code to non-Claude models through a gateway. It works because Redline translates the Messages API, but it is not a configuration Anthropic backs.