Skip to main content
REST API v1.0

One API.
352+ models.
Five modalities.

Image, video, voice, music, and 3D generation through a single REST API. Every response includes the exact cost in dollars.

GPT Image 1.5 · FLUX.1 Pro · Veo 3 · Runway Gen-4 · ElevenLabs · Suno · Kling 2.1 · and 345+ more

Get API Key Read Documentation
terminal 
curl -X POST https://api.fairstack.ai/v1/generations/image \
  -H "Authorization: Bearer $FAIRSTACK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-image-1.5","prompt":"A mountain lake at sunrise"}'

# Response
{
  "id": "gen_abc123",
  "url": "https://media.fairstack.ai/...",
  "model": "gpt-image-1.5",
  "cost": {
    "amount": 0.009,
    "currency": "USD"
  }
}
352+
AI Models
5
Modalities
99.9%
Uptime SLA
$0
Monthly Fee

The API sprawl problem.

Every new modality means another provider, another dashboard, another billing system, another set of docs.

Without FairStack
OpenAI — images, separate billing
Replicate — video, GPU-second pricing
ElevenLabs — voice, credit-based tier
Suno — music, subscription only
4 dashboards. 4 billing systems. 4 auth flows. 4 sets of docs.
With FairStack
One API key for all modalities
One billing dashboard in real dollars
One set of docs, one SDK
Switching models = changing one parameter
352+ models. One integration.

Three lines to generate anything.

Same SDK, same pattern, every modality. Switch from image to video by changing the method call.

Image @fairstack/sdk 
import FairStack from "@fairstack/sdk";

const fs = new FairStack();

const image = await fs.image.generate({
  model: "gpt-image-1.5",
  prompt: "A mountain lake",
});

console.log(image.url);
// cost: $0.009
Voice @fairstack/sdk 
import FairStack from "@fairstack/sdk";

const fs = new FairStack();

const audio = await fs.voice.generate({
  model: "elevenlabs-v2",
  text: "Welcome to the show",
});

console.log(audio.url);
// cost: $0.001
Video @fairstack/sdk 
import FairStack from "@fairstack/sdk";

const fs = new FairStack();

const video = await fs.video.generate({
  model: "kling-2.1",
  prompt: "A timelapse of clouds",
});

console.log(video.url);
// cost: $0.08

Also available: pip install fairstack for Python

APIs for every creative modality.

One API key. 352+ models across image, video, voice, and music. Switch models in one line of code.

Image Generation

/v1/generations/image

142 models including GPT Image 1.5, FLUX.1 Pro, Seedream 4.5, Ideogram 3.0, and Recraft V3. Text-to-image, image-to-image, inpainting, upscaling.

From $0.003/image

GPT Image 1.5 FLUX.1 Pro Seedream 4.5 Ideogram 3.0 Recraft V3

Video Generation

/v1/generations/video

104 models including Veo 3, Kling 2.1, Runway Gen-4, Wan 2.1, and Hunyuan. Text-to-video, image-to-video, video extend, restyle.

From $0.04/clip

Veo 3 Kling 2.1 Runway Gen-4 Wan 2.1 Hunyuan

Voice & TTS

/v1/generations/voice

17 models including ElevenLabs V2, CosyVoice 2, Kokoro, and FishSpeech. Text-to-speech, voice cloning, emotion control. 168 built-in voices.

From $0.001/clip

ElevenLabs V2 CosyVoice 2 Kokoro FishSpeech

Music Generation

/v1/generations/music

8 models including Suno V4.5, YuE, DiffRhythm, and ACE-Step. Text-to-music, lyrics-to-song, instrumental generation. Up to 8 minutes per track.

From $0.018/song

Suno V4.5 YuE DiffRhythm ACE-Step

Real dollar pricing. No credits.

Every API response includes the exact cost in USD. Infrastructure cost + 20% margin = your price. We publish the math.

  • Every response includes cost in USD
  • Call /v1/cost-estimate before generating
  • No credits to decode, no token math
  • 20% margin on infra cost — published formula
Model Direct FairStack
GPT Image 1.5 $0.027 $0.009
Runway Gen-4 $0.50 $0.05
ElevenLabs V2 $0.30/min $0.126/min
Veo 3 $0.50 $0.15
See full pricing calculator →

Built for production.

Not just another model aggregator. Full cost controls, structured errors, and real documentation.

Scoped API Keys

Create keys with granular permissions: restrict by modality, set per-request cost limits, and set total spending caps. Revoke instantly.

3-Level Spending Caps

Hard limits at organization, project, and API key level. Requests exceeding caps get a 429, not an invoice. Safe for autonomous agents.

Webhooks

Register endpoints per org. Get notified on generation.completed, generation.failed, and balance.low events. Automatic retries with delivery logs.

Cost Simulation

Call /v1/cost-estimate before generating. Know the exact price, choose the model, then execute. No other API does this.

Structured Errors

Every error includes a machine-readable code, human message, and request trace ID. No guessing what went wrong.

MCP Server

Agent-native integration for Claude, GPT, and custom agents. Your AI can generate images, video, and audio as tool calls.

Integrate in minutes.

REST API, webhooks, SDKs, and MCP -- everything you need to ship.

Quickstart

First generation in under 5 minutes.
API Reference

35+ endpoints, full OpenAPI spec.
SDKs

TypeScript and Python. npm/pip install.
MCP Server

Agent-native integration for Claude, GPT, etc.

Ship AI features this week.

352+ models. One API key. No subscription. No monthly fee.

Get API Key Read the Docs