Docs

Drop in. Route smart. Cut costs.

A drop-in replacement for the OpenAI and Anthropic base URLs. Pick a section, or start with the three-line quickstart.

Most agent loops pin one expensive model across every step, from planning to retrieval to tool calls to synthesis to verification, and pay frontier prices throughout. Fairmeter classifies each step and sends it to the cheapest model that still holds quality, then serves repeats from cache instead of billing you twice.

Quickstart Open the demo

Quickstart

Switch the OpenAI base URL to the gateway in three lines.

Open

API reference

Auto-generated from the gateway's OpenAPI schema.

Open

SDK recipes

Runnable templates for OpenAI, Anthropic, curl, LangChain, Cursor, Codex CLI, and Claude Code.

Open

quickstart.sh

curl https://gateway.fairmeter.in/v1/chat/completions \
  -H "Authorization: Bearer gw_live_..." \
  -H "Content-Type: application/json" \
  -d '{ "model": "cap:auto", "messages": [...] }'

Core concepts

Auth

How API keys, scopes, and the gw_live_ prefix work.

Routing

How the gateway picks a model and a none/low/medium/high thinking budget per prompt.

Step classifier

Per-step labels that bias routing across an agent loop.

Capability aliases

Name intent with cap: handles instead of pinning models.

Agent sessions

One row per agent run: trajectory replay and cost envelopes.

Caching

Exact, semantic, multi-turn, and streaming cache hits, billed at zero.

Billing

Token classes, four-way spend split, and thinking-budget reporting.

Tooling

IQ CLI

Local terminal for the gateway: prompt, batch, generate-prompts.

Key vault

Recover plaintext for issued API keys, PATs, and provider credentials.

Token optimizer

Safe and aggressive payload compression before the upstream call.

Webhooks

Stream audit events to a SIEM, chat, or incident pipeline.

Security & ops

Security

Zero data retention, anomaly rate-limits, access scoping, and per-org controls.

Compliance

Audit chain, evidence packs, GDPR DSAR, and HIPAA-oriented tooling.

Operations

Exactly-once daily jobs, dependency currency, and what an operator can verify.

Webhook capacity

Size your receiver for the delivery rate, latency budget, and retry behaviour.

Reference

SDKs

Typed clients and framework adapters.

API reference

Every endpoint, request, and response shape.

FAQ

Prompt storage, zero data retention, provider keys, rate-limit scopes, tracing.

Three lines today. A clean bill tomorrow.

Plans start at $9.99/month. You’ll route real traffic in under five minutes.

Get started Read the quickstart