Relyven API quickstart

This guide verifies the base URL, API key, model permission, and one real request. Use the protocol your client expects.

Step 1: Create an API key

Sign in to the dashboard, open API Keys, and create a key. Store it in an environment variable and never commit it to source control. See Account and API keys for lifecycle guidance.

Step 2: Choose a protocol

Client	Base URL	Primary endpoint
OpenAI-compatible SDKs, Codex, Cline	https://api.relyven.com/v1	/responses or /chat/completions
Claude Code, Anthropic SDK	https://api.relyven.com	/v1/messages

Step 3: Verify authentication and models

curl https://api.relyven.com/v1/models \
  -H "Authorization: Bearer $RELYVEN_API_KEY"

A 200 response confirms the base URL and key. A 401 means the key or header is wrong. A model missing from the list may be unavailable to that key.

Step 4: Make a request

OpenAI Responses

curl https://api.relyven.com/v1/responses \
  -H "Authorization: Bearer $RELYVEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"YOUR_MODEL_ID","input":"Reply with OK."}'

Copy the exact model ID from the dashboard. Do not guess aliases.

Anthropic Messages

curl https://api.relyven.com/v1/messages \
  -H "x-api-key: $RELYVEN_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model":"YOUR_CLAUDE_MODEL_ID",
    "max_tokens":256,
    "messages":[{"role":"user","content":"Reply with OK."}]
  }'

Messages requires max_tokens. Use a Claude model returned for the current key.

Next steps

• CC Switch: Configure CC Switch
• Claude Code: Direct custom API setup
• Codex: Direct custom provider setup
• Failures: Error handling