Connect your local AI agent to WaveSpeed LLM
Pick an agent, choose a WaveSpeed model, copy the right local config file, and route requests through the protocol that agent expects.
Use WaveSpeed through Claude Code's Anthropic-compatible gateway mode.
~/.claude/settings.json
Anthropic Messages API
/v1/messages
Manual setup
Create a WaveSpeed access key
Export the required key locally
Paste config into~/.claude/settings.json
Run claude and check Logs
OpenAI-compatible chat completions
Usage appears in Dashboard and Logs
Switch models without rewriting agent code
One-command setup
Configures Claude Code, checks that it works, and backs up your previous settings. Add --undo to restore them.
- 1
Install the WaveSpeed CLI
npm install -g @wavespeed/cli - 2
Sign in
wavespeed login - 3
Configure Claude Code
wavespeed setup claude
No Node.js? See other install options
Claude Desktop is set up in its own settings, not with this command. See the Claude Desktop guide
Manual setup
{
"env": {
"ANTHROPIC_AUTH_TOKEN": "wsk_live_...",
"ANTHROPIC_BASE_URL": "https://llm.wavespeed.ai",
"ANTHROPIC_MODEL": "deepseek/deepseek-v4.1-flash-1017",
"ANTHROPIC_DEFAULT_OPUS_MODEL": "deepseek/deepseek-v4.1-flash-1017",
"ANTHROPIC_DEFAULT_SONNET_MODEL": "deepseek/deepseek-v4.1-flash-1017",
"ANTHROPIC_DEFAULT_HAIKU_MODEL": "deepseek/deepseek-v4.1-flash-1017"
}
}