Files
exo/tmp/config_examples/claude_code.sh
rltakashige 423ed0f07f Strip Claude headers to improve prefix cache hit rates (#1552)
## Motivation
Our hits are really bad at the moment (0.2%). This PR makes it 98.5% on
average.

## Changes

Also adds an example for how to run Claude using Exo.

## Why It Works
Claude sends some billing and session headers that change with each
message.

## Test Plan

### Manual Testing
Works in manual testing.
2026-02-19 18:29:34 +00:00

9 lines
343 B
Bash
Executable File

#!/bin/bash
# Run Claude Code against a local exo cluster! (Here, GPT OSS 120B)
ANTHROPIC_BASE_URL="http://localhost:52415/" \
ANTHROPIC_AUTH_TOKEN="dummy" \
ANTHROPIC_MODEL="mlx-community/gpt-oss-120b-MXFP4-Q8" \
ANTHROPIC_SMALL_FAST_MODEL="mlx-community/gpt-oss-120b-MXFP4-Q8" \
CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 \
claude