How do I start calling AI models through AIgateway?

Point the official OpenAI SDK at https://api.aigateway.sh/v1 with your AIgateway API key, then call chat.completions.create with any model ID from /v1/models. No other changes required. See /docs/first-request.

Is AIgateway a drop-in OpenAI replacement?

Yes. The request body, streaming SSE format, and error shapes match OpenAI exactly. Existing integrations with Anthropic, Google, Groq, Mistral, xAI, Moonshot all work through the same endpoint.

How do I call Claude, Gemini, or Kimi through AIgateway?

Change the model field: anthropic/claude-opus-4.7, google/gemini-3.1-pro, moonshot/kimi-k2.6. Every model in /v1/models uses the same request shape.

Does AIgateway support streaming, tool calling, vision, and JSON mode?

Yes, on every model where the upstream provider supports it. Capabilities are published per-model in /v1/models and on each /models/ page.

How does billing work?

Pass-through on upstream model cost plus a 5% platform fee applied at credit top-up. Cached requests get a 50% discount. No per-call fee, no monthly minimum. See /pricing.

Can I bring my own API keys (BYOK) for OpenAI, Anthropic, or Google?

Yes. Attach provider keys in the dashboard and routing flips to pass-through — you pay the provider directly, and AIgateway waives the 5% fee on those calls. See /docs/byok.

View as /docs.md

Getting started

Introduction

AIgateway is one OpenAI-compatible API for 1000+ frontier and open-weight models. You write your code once, against one base URL, and swap providers by changing a string in the model field. Billing, routing, fallbacks, caching, and observability are handled for you at the edge.

$5 signup credit · no card required. Every new account gets $5 in credit spendable on a curated 7-model edge tier — moonshot/kimi-k2.6, baai/bge-m3, black-forest-labs/flux-2-klein-9b, google/gemma-4-26b-a4b-it, deepgram/aura-2-en, openai/whisper-large-v3-turbo, meta/llama-guard-3-8b. The credit expires 7 days after signup. Top up any amount to unlock the full catalog at PAYG rates.

Fastest integration path

Agent setup wizard

Choose your stack once. Copy the generated blocks and get to first successful request in under 2 minutes.

AgentLanguageDefault modelAPI key env name

0) Copy full starter pack

# 0) Install
pnpm add aigateway-js openai

# 1) Environment
# .env.local
AIG_KEY=sk-...

# 2) First request
// pnpm add aigateway-js openai   (or npm / yarn)
// aigateway-js: sub-accounts, evals, replays, jobs, webhook verify.
// openai SDK: chat/embeddings/images/audio — drop-in compat per our SDK's own guidance.
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.AIG_KEY,
  baseURL: "https://api.aigateway.sh/v1",
});

const res = await client.chat.completions.create({
  model: "moonshot/kimi-k2.6",
  messages: [{ role: "user", content: "Write a haiku about edge inference." }],
});

console.log(res.choices[0]?.message?.content);

# 3) Claude Code rule/instruction
# CLAUDE.md snippet
Use AIgateway for all AI calls.
- Base URL: https://api.aigateway.sh/v1
- Auth env: AIG_KEY
- Default model: moonshot/kimi-k2.6
- Docs page: https://aigateway.sh/docs
- MCP endpoint: https://api.aigateway.sh/mcp

# 4) MCP setup
claude mcp add aigateway https://api.aigateway.sh/mcp -t http -h "Authorization: Bearer $AIG_KEY"

# 5) Smoke test command
curl https://api.aigateway.sh/v1/models \
  -H "Authorization: Bearer $AIG_KEY" \
  -H "Content-Type: application/json"

1) Install

pnpm add aigateway-js openai

2) Environment variable

# .env.local
AIG_KEY=sk-...

3) First request snippet

// pnpm add aigateway-js openai   (or npm / yarn)
// aigateway-js: sub-accounts, evals, replays, jobs, webhook verify.
// openai SDK: chat/embeddings/images/audio — drop-in compat per our SDK's own guidance.
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.AIG_KEY,
  baseURL: "https://api.aigateway.sh/v1",
});

const res = await client.chat.completions.create({
  model: "moonshot/kimi-k2.6",
  messages: [{ role: "user", content: "Write a haiku about edge inference." }],
});

console.log(res.choices[0]?.message?.content);

4) Claude Code rule/instruction

# CLAUDE.md snippet
Use AIgateway for all AI calls.
- Base URL: https://api.aigateway.sh/v1
- Auth env: AIG_KEY
- Default model: moonshot/kimi-k2.6
- Docs page: https://aigateway.sh/docs
- MCP endpoint: https://api.aigateway.sh/mcp

5) MCP setup command

claude mcp add aigateway https://api.aigateway.sh/mcp -t http -h "Authorization: Bearer $AIG_KEY"

6) Smoke test command (terminal)

curl https://api.aigateway.sh/v1/models \
  -H "Authorization: Bearer $AIG_KEY" \
  -H "Content-Type: application/json"

Run smoke test in browser: paste a test key and validate auth + reachability instantly.

Verify full integration: run the first request snippet, then confirm response + usage in Dashboard logs. If it fails, use Error codes and Your first request.

The learn path

These four pages take you from zero to a streaming response in under three minutes. Go in order — every other topic assumes you've done this first.

1. Authentication

Mint a key, pin it on the client, scope it by tier.

2. Your first request

OpenAI-compatible chat completion in Python, Node, or curl.

3. Swap models

One body shape, 1000+ model IDs — how routing works.

4. Streaming

SSE chunks with first-token latency under 500ms.

Explore by topic

Once you've shipped your first request, the rest of the docs are reference material — read in any order.

Need more than docs?

Live Playground — test any model in the browser.
Full API reference — every endpoint with request / response schemas.
The model catalog — pricing, context, capabilities for all 1000+.
For agents: /agents describes the /llms.txt manifest + MCP setup.

Next →Authentication

Introduction

Agent setup wizard

The learn path

Explore by topic

Inference

Return modes

Platform

Reference

Need more than docs?