API Reference

Overview

gateway.fast exposes inference endpoints under https://api.gateway.fast/v1. Requests are routed in real time to the best available model. You can influence routing via request headers — or let gateway.fast decide automatically.

Two routing modes are available:

• Auto mode (default) — gateway.fast classifies your request and picks the optimal model by tier, live load, and workload type.
• Direct mode — You specify exactly which model to use via x-model.

Some models are TEE-enabled. The model catalog shows which models support TEE.

Authentication

All requests require a Bearer token in the Authorization header. API keys are issued after purchase at gateway.fast/pricing and follow the format sk-gw-….

Authorization: Bearer sk-gw-<your-api-key>

Quick start

Send your first request in under a minute:

curl -X POST https://api.gateway.fast/v1/messages \
  -H "Authorization: Bearer sk-gw-<your-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      { "role": "user", "content": "Summarise the key steps of a RAG pipeline." }
    ],
    "max_tokens": 1024
  }'

POST /v1/messages

The primary inference endpoint. Accepts a messages payload and returns a completion.

Request body

POST /v1/chat/completions

An OpenAI-compatible alias that delegates to /v1/messages. Use this as a drop-in replacement if your SDK or framework targets the OpenAI API format.

Routing headers

These request headers control how gateway.fast routes your request. All are optional — omitting them triggers fully automatic routing.

Auto mode

In auto mode, gateway.fast uses a two-stage routing pipeline:

1. LLM classifier — A lightweight Claude call analyses your messages for signals: agentic intent, tool use, code, reasoning depth, latency sensitivity. Completes in under 2 seconds.
2. Availability-weighted scorer — Combines capability tier score with live availability data to pick the model least likely to be rate-limited right now.

If the classifier times out, routing falls back to the heuristic scorer alone — no request is dropped.

curl -X POST https://api.gateway.fast/v1/messages \
  -H "Authorization: Bearer sk-gw-<your-key>" \
  -H "Content-Type: application/json" \
  -H "x-latency: low" \
  -H "x-privacy: tee" \
  -d '{
    "messages": [{ "role": "user", "content": "Fix this bug: ..." }],
    "tools": [{ "name": "bash", "description": "Run shell commands" }],
    "max_tokens": 2048
  }'

Direct mode

Use x-mode: direct with x-model to target a specific model. The availability scorer is bypassed — your request goes to exactly the model you specify.

curl -X POST https://api.gateway.fast/v1/messages \
  -H "Authorization: Bearer sk-gw-<your-key>" \
  -H "Content-Type: application/json" \
  -H "x-mode: direct" \
  -H "x-model: kimi-k2.6-tee" \
  -d '{
    "messages": [{ "role": "user", "content": "..." }],
    "max_tokens": 4096
  }'

Response headers

Every response includes metadata headers describing what happened:

Streaming

Set "stream": true in your request body to receive a Server-Sent Events stream. Each event follows the standard SSE format with a data: prefix. The stream terminates with data: [DONE].

import requests, json

resp = requests.post(
    "https://api.gateway.fast/v1/messages",
    headers={
        "Authorization": "Bearer sk-gw-<your-key>",
        "Content-Type": "application/json",
    },
    json={
        "messages": [{"role": "user", "content": "Write a sorting algorithm."}],
        "max_tokens": 2048,
        "stream": True,
    },
    stream=True,
)

for line in resp.iter_lines():
    if line and line.startswith(b"data: "):
        data = line[6:]
        if data == b"[DONE]":
            break
        chunk = json.loads(data)
        print(chunk, flush=True)

Errors

All errors return JSON with an error field describing the issue.

Model catalog

The active model catalog is exposed through GET /v1/models. Provider names are shown as gateway.fast in customer-facing surfaces.

Tier system

Models are grouped into four capability tiers. Auto routing uses tiers as a primary signal alongside live utilisation.