Setup prompts
Paste one prompt into a coding agent and it wires the gateway for you, asking before every write.
How to use them
Open a prompt, press Copy, paste it into a CLI coding agent (Claude Code, Codex, OpenCode and the like). Add your key with Add API key first and it is filled in. Each prompt asks before editing files and never prints more than the first 8 characters of a key. Per-agent configuration by hand is on Coding agents.
GET/v1/modelscurl https://api.experientiallabs.ai/v1/models \
-H "Authorization: Bearer YOUR_API_KEY"Set up the gateway in a project
Finds the existing client, swaps base URL and key, makes one call.
curl https://api.experientiallabs.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-6-luna", "max_tokens": 32, "messages": [{"role": "user", "content": "reply with the single word: ok"}]}'Wire any coding agent
The agent identifies itself and applies its own integration. Per-agent prompts are on Coding agents.
ANTHROPIC_BASE_URL="https://api.experientiallabs.ai" \
ANTHROPIC_API_KEY="YOUR_API_KEY" \
ANTHROPIC_MODEL="claude-opus-5" \
claudeIntegrate into your product
Attributes each request to your end customer and builds a billing sync on the settled usage export.
GET/api/v1/usagecurl https://api.experientiallabs.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-6-luna", "safety_identifier": "customer-42", "messages": [{"role": "user", "content": "Hi"}]}'Switch from another gateway
Moves an OpenRouter, LiteLLM, Portkey or other integration. The full diff is on Switch from OpenRouter.
GET/api/v1/modelscurl https://api.experientiallabs.ai/api/v1/models \
-H "Authorization: Bearer YOUR_API_KEY" | jq '.data[] | {id, canonical_slug}'Bring your own provider keys
Connects several provider accounts at once. A first connection needs Pro. See BYOK.
POST/api/orgs/{org_id}/provider-connections/{provider}curl -X POST https://api.experientiallabs.ai/api/orgs/ORG_ID/provider-connections/openai \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"setup_alias": "openai-work", "secret": "sk-...", "config": {}}'Set up identities (provisioning key)
Creates identities with one inference key each, so spend buckets per identity.
POST/api/orgs/{org_id}/identitiescurl "https://api.experientiallabs.ai/api/orgs/ORG_ID/usage/by-identity?window=7d" \
-H "Authorization: Bearer YOUR_API_KEY"Read your traffic
Answers "why did requests fail today?" from the request log. Any key of your org can read it, prompt bodies included while capture is on.
GET/api/orgs/{org_id}/usage/requestscurl "https://api.experientiallabs.ai/api/orgs/ORG_ID/usage/requests?window=24h&status=error" \
-H "Authorization: Bearer YOUR_API_KEY"Turn on zero data retention
One audited call: capture off, ZDR routing and no-training routing on. Pro feature. See Data controls.
PUT/api/orgs/{org_id}/zero-data-retentioncurl -X PUT https://api.experientiallabs.ai/api/orgs/ORG_ID/zero-data-retention \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"enabled": true}'