Your free credit covers a curated edge-tier shortlist — Kimi K2.6 for chat, FLUX-2 Klein for image, Whisper Turbo + Aura 2 for voice, BGE-M3 for embeddings, Gemma 4 for vision, Llama Guard for moderation. Top up to unlock the full catalog; topups never expire.
from openai import OpenAI client = OpenAI( base_url="https://api.aigateway.sh/v1", api_key="sk-aig-...", ) r = client.chat.completions.create( model="anthropic/claude-opus-4.7", messages=[{"role": "user", "content": "Plan a" " research agent."}], stream=True, ) # $5 free credit on signup (7-day window, curated models). # Top up to unlock the full 1000+-model catalog.
Drop-in compatible with the OpenAI SDK. Rotate models mid-conversation without changing any other line of code.
Anonymized competitor labels — same public pricing and feature matrix, minus the trash talk. We'll let you Google who's who.
| AIgateway | Competitor A breadth aggregator | Competitor B platform-native gateway | Competitor C enterprise governance | |
|---|---|---|---|---|
| Models / modalities | 1000+ · text · image · video · music · voice · audio · embeddings · vision | ~300 · text only | ~40 · text + image | ~80 · image, video, audio |
| Open-weight served at the edge | yes | no · pass-through | no · pass-through | no · queue |
| Edge latency (p50) | 47ms · global edge | ~180ms · single region | ~60ms · one platform | ~190ms · single region |
| Eval-driven routing (SLO on your data) | yes | — | — | — |
| Sub-account / per-user key API | yes · programmatic | — | workspace only | — |
| Replay + shadow A/B across models | yes | — | — | — |
| OpenAI-compatible | drop-in, zero changes | drop-in | drop-in | — |
Sourced from each competitor's public pricing page and docs, April 2026. If something is wrong, email hello@aigateway.sh and we'll fix it.
1000+ models across 85+ labs — text, image, video, music, voice, audio, embeddings, vision. Same OpenAI-compatible body shape for every one. Rotate between Claude Opus 4.7, GPT-5.4, Gemini 3.1 Pro, Kimi K2.6, Llama 4, Flux 1 Schnell, Stable Diffusion XL, Veo 3.1, MiniMax Hailuo by changing a single string.
Things single-provider SDKs physically cannot do — because they only see one provider. We see all of them.
curl -X POST https://api.aigateway.sh/v1/evals \
-H "Authorization: Bearer $KEY" \
-d '{
"name": "prod-summarize",
"candidate_models": [
"anthropic/claude-opus-4.7",
"openai/gpt-5.4",
"moonshot/kimi-k2.6"
],
"dataset": [...],
"metric": "quality"
}'
# then just use it
model = "eval:prod-summarize"POST /v1/sub-accounts
{
"name": "acme-corp",
"spend_cap_cents": 50000, // $500 / mo hard cap
"rate_limit_rpm": 300,
"default_tag": "acme"
}
=> { "key": "sk-aig-...", // hand to customer
"spend_cap_cents": 50000,
"id": "sa_9f3k..." }POST /v1/replays
{
"source_request_id": "req_abc123",
"target_model": "anthropic/claude-opus-4.7",
"shadow": true
}
=> { "source_output": "...",
"target_output": "...",
"cost_source_cents": 1.2,
"cost_target_cents": 4.7,
"score_delta": 0.82 }# tag each request with the feature it powers
curl https://api.aigateway.sh/v1/chat/completions \
-H "x-aig-tag: summarize" \
...
GET /v1/usage/by-tag?month=2026-04
=> [{ "tag": "summarize", "cost_cents": 4210 },
{ "tag": "chat", "cost_cents": 9830 },
{ "tag": "rerank", "cost_cents": 118 }]A capable coding agent reads /llms.txt, /openapi.json, or /agents.md once — and from then on it can call every modality, mint sub-accounts, tag cost, and replay requests without a human editing config.
You can call any AI model through AIgateway, a universal AI API. - Base URL: https://api.aigateway.sh/v1 - Auth: Authorization: Bearer sk-aig-... - SDK: drop-in for the OpenAI SDK — only change base_url - OpenAPI spec: https://api.aigateway.sh/openapi.json - Capability map: https://aigateway.sh/llms.txt - Live models: https://api.aigateway.sh/v1/models - MCP server: https://api.aigateway.sh/mcp Install (only when the OpenAI SDK isn't enough): pip install aigateway-py # Python — async jobs, sub-accounts, evals pnpm add aigateway-js # Node — same surface in TypeScript npm i -g aigateway-cli # CLI — `aig init` walks through everything Primitives nobody else has: POST /v1/sub-accounts — scoped keys + spend caps per end user POST /v1/evals — grade candidate models on your data POST /v1/replays — re-run a past request on a new model GET /v1/usage/by-tag — per-feature cost via x-aig-tag header
Sign up in 30 seconds — no waitlist, no sales call. Cline, Aider, and a handful of agent startups are already on it. Want a personal onboard? Drop your email and I'll reply.