Unlimited Open Source Models

Get Plan
Skip to main content

Replace 10+ API Providers with ModelsLab

AI API Pricing for Every Developer

99.9% Uptime<200ms API Response500M+ API Requests Processed

Switching from another API provider? Compare us with fal.ai or Replicate

100% refund policy on monthly & yearly plans — cancel anytime

Contact Sales
Best Value

Open Source Unlimited

Mission-Critical

$149/month

100% refund policy · cancel anytime

Unlimited Open Source Models
100% refund policy
24x7 Support
15 parallel generations
Access to all APIs
Unlimited generations on all open-source models
For mission critical workloads
Add Team Members
Priority GPU Clusters
Most Popular

Standard

Production

$47/month

100% refund policy · cancel anytime

Moderate Traffic
100% refund policy
Priority Developer Support
10 concurrent API requests
For Production workloads
API access to all models
Prototype

Basic

Prototype

$21/month

100% refund policy · cancel anytime

Moderate Traffic
100% refund policy
Developer Support via Discord/Email
5 concurrent API requests
API access to all models
Shared GPU
Frequently Asked Questions

Everything You Need to Know

Get answers to common questions about pricing, features, and integration.

Get Expert Support in Seconds

We're Here to Help.

Want to know more? You can email us anytime at support@modelslab.com

View Docs

Yes — on the $149/month Open Source Unlimited plan, every open-source model (Flux, SDXL, Qwen, WAN, and more) hosted on our own infrastructure gives you unlimited generations with zero credit deduction. You also get 15 parallel API requests, so multiple generations can run at once instead of queuing one by one.

Yes, if you plan to use any premium third-party model. The $149/month subscription covers unlimited open-source generations and 15 parallel requests — it doesn't include any wallet credit. Add funds separately whenever you want to call Google, Kling, Seedance, or other premium APIs.

No. ModelsLab is paid-only — there is no free tier, no free credits and no trial plan. Plans start at $21/month (Basic), which includes 3,250 API calls and access to every model in the catalogue. To judge a model before subscribing, open its page: each one shows example outputs and the exact request body you would send.

Yes. Wallet top-ups are for active subscribers, which is why no "Add Funds" option appears on an account with no plan. Subscribe to any plan and wallet funding unlocks. Accounts that already held a wallet balance keep the ability to top up.

Your plan allowance resets at the start of each billing period and unused allowance does not carry forward. Wallet balance works differently: money you have topped up stays on the account until you spend it, and is not cleared when the plan renews.

Open-source models we host ourselves — Flux, SDXL, SD 1.5, WAN and similar — are unlimited on the $149/month Open Source Unlimited plan. Premium third-party models such as Google, Kling, Seedance, Vidu and ByteDance are billed per call from your wallet on every plan, including the unlimited one. The pricing tables on this page carry an "Unlimited" column marking exactly which models are included.

Video is priced per second of output or as a multiplier on the model's base rate, depending on the provider — the exact rate for each model is in the AI Video table on this page. A single video clip can cost considerably more than an image, so check the rate for your chosen model before running a batch.

Basic at $21/month includes 3,250 API calls and 5 concurrent requests. Standard at $47/month includes 10,000 calls and 10 concurrent requests. Open Source Unlimited at $149/month removes the call limit on open-source models and allows 15 concurrent requests. Every plan can reach every model — plans differ on volume and concurrency, never on which models you may use.

Cancel from Dashboard → Subscription at any time. Cancelling stops future renewals and you keep access until the end of the period you have already paid for. Monthly and yearly plans carry a 100% refund policy — email support@modelslab.com if you would like a refund processed or if the cancellation flow does not complete for you, and we will handle it directly.

Yes. Output you generate through the API is yours to use commercially on every paid plan. Individual third-party models can carry their own upstream licence terms, so check the model page if you are building on one specific closed-source provider.

Yes. The agent control plane at /api/agents/v1 covers the whole lifecycle: POST /auth/signup creates the account, POST /billing/payment-link returns a Stripe checkout URL, POST /subscriptions starts a plan, and POST /api-keys issues the key. An agent can go from no account to a working API key without a browser. Plans start at $21/month for 3,250 API calls; ModelsLab is paid-only, so a subscription is required before generation.

AI Models Pricing by Feature

ModelsLab meters usage per API call based on the model used. Image generation starts at $0.0047 per image, video generation from $0.02 per second, audio synthesis from $0.001 per second, and LLM inference from $0.20 per million tokens. Models marked Unlimited are included in the unlimited plan.

AI Image

85 models available

Model NameProviderPriceUnlimited plan$149/mo Open Source
Qwen Image 2.0 Pro Text To ImageAlibaba Cloud
$0.07500Per Generation
Billed per call
Qwen Image 2.0 Pro Image EditAlibaba Cloud
$0.07500Per Generation
Billed per call
Wan 2.7 Image EditAlibaba Cloud
$0.03000Per Generation
Billed per call
Wan 2.7 Text To ImageAlibaba Cloud
$0.03000Per Generation
Billed per call
Qwen Image 3.0 Text To ImageAlibaba Cloud
$0.07500Per Generation
Billed per call
Flux Kontext ProBFL
$0.04800Per Generation
Billed per call
Flux 2 Pro Text To ImageBFL
$0.05400Per Generation
Billed per call
Flux 2 Pro Image EditingBFL
$0.05400Per Generation
Billed per call
Flux 2 Max Image EditingBFL
$0.24000Per Generation
Billed per call
Flux 2 Max Text To ImageBFL
$0.24000Per Generation
Billed per call

AI Audio

23 models available

Model NameProviderPriceUnlimited plan$149/mo Open Source
Eleven multilingual v2Elevenlabs
$0.00400Per Second
Billed per call
Scribe v1Elevenlabs
$0.00100Per Second
Billed per call
Elevenlabs Voice ChangerElevenlabs
$0.00500Per Second
Billed per call
ElevenLabs Sound EffectsElevenlabs
$0.06000Per Generation
Billed per call
MusicElevenlabs
$0.00700Per Second
Billed per call
Eleven V3 Text To SpeechElevenlabs
$0.02000Per Second
Billed per call
Lyria 3 Google
$0.05000Per Generation
Billed per call
Inworld Text to SpeechInworld
$6.00000Per Million Characters
Billed per call
Voice isolationModelsLab
$0.00100Per Second
Yes
Qwen Text to SpeechModelsLab
$0.00100Per Second
Yes

AI Video

95 models available

Model NameProviderPriceUnlimited plan$149/mo Open Source
Wan 2.5 Text to VideoAlibaba Cloud
$0.50000Multiplier
Billed per call
Wan 2.5 Image to VideoAlibaba Cloud
$0.50000Multiplier
Billed per call
Wan2.6 Image To Video Alibaba Cloud
$0.50000Multiplier
Billed per call
Wan2.6 Text To Video Alibaba Cloud
$0.50000Multiplier
Billed per call
Wan2.6 Image To Video (Flash)Alibaba Cloud
$0.10000Multiplier
Billed per call
WAN 2.7 Text To VideoAlibaba Cloud
$0.50000Multiplier
Billed per call
WAN 2.7 Image To VideoAlibaba Cloud
$0.50000Multiplier
Billed per call
Happyhorse-1.0-t2vAlibaba Cloud
$0.14000Multiplier
Billed per call
Happyhorse-1.0-i2vAlibaba Cloud
$0.14000Multiplier
Billed per call
Happyhorse-1.0-video-editAlibaba Cloud
$0.14000Multiplier
Billed per call

AI Chat

355 models available

Model NameProviderPriceUnlimited plan$149/mo Open Source
Qwen: Qwen3.5 397B A17BAlibaba Cloud
$2.10000Per Million Tokens
Billed per call
Qwen: Qwen3.5-35B-A3BAlibaba Cloud
$1.12500Per Million Tokens
Billed per call
Qwen: Qwen3.5-27BAlibaba Cloud
$1.35000Per Million Tokens
Billed per call
Qwen: Qwen3.5-122B-A10BAlibaba Cloud
$1.80000Per Million Tokens
Billed per call
Arcee AI SpotlightArcee Ai
$0.21600Per Million Tokens
Billed per call
Arcee AI Coder-LargeArcee Ai
$0.65000Per Million Tokens
Billed per call
Seed 1.8Byteplus
$3.00000Per Million Tokens
Billed per call
DeepSeek-R1Deepseek
$2.00000Per Million Tokens
Billed per call
DeepSeek V3-0324Deepseek
$0.48500Per Million Tokens
Billed per call
DeepSeek R1 Distill Qwen 14BDeepseek
$1.60000Per Million Tokens
Billed per call

AI 3D

2 models available

Model NameProviderPriceUnlimited plan$149/mo Open Source
Text to 3DModelsLab
$0.07500Per Generation
Yes
Image to 3DModelsLab
$0.07500Per Generation
Yes

What's Included in Every Plan

Access to all these powerful AI APIs with a single subscription

AI Image Generation

Production-ready AI Image generation APIs

Specifications
Response Time:~2-4s
Throughput:1000+ req/min
Formats:PNG, JPG, WebP
Key Features
  • SDXL & Flux models
  • Image editing
  • Batch processing
  • CDN delivery

AI Video Generation

Text-to-video and video editing APIs

Specifications
Response Time:~30-120s
Throughput:100+ req/min
Formats:MP4, WebM, GIF
Key Features
  • Text to Video
  • Video Editing
  • Custom duration
  • Long videos
  • Watermark removal

AI 3D Assets Generation

3D model and texture generation

Specifications
Response Time:~60-300s
Throughput:50+ req/min
Formats:GLB, OBJ, FBX
Key Features
  • Text-to-3D
  • Image to 3D
  • Multiple formats
  • UV mapping

AI Audio Generation

Voice cloning and audio generation

Specifications
Response Time:~1-5s
Throughput:500+ req/min
Formats:MP3, WAV, FLAC
Key Features
  • Voice cloning
  • Text-to-speech
  • Music generation
  • in 40+ languages

Custom trained LLMs

Custom trained language models

Specifications
Response Time:~500ms
Throughput:10k+ tokens/min
Formats:10+ LLMs
Key Features
  • Multiple LLM models
  • Open-source models
  • Streaming support
  • Custom prompts

Quick Integration

  • RESTful API with JSON responses
  • Comprehensive documentation
  • SDKs for popular languages
  • Postman collection available
  • WebSocket streaming support

Enterprise Features

  • 99.9% uptime SLA guarantee
  • Dedicated account manager
  • Priority technical support
  • Custom rate limits
  • Advanced analytics dashboard

Popular API Pricing Guides

Start with the pricing guides that match how developers actually search for AI APIs.

DeepSeek API Pricing

Pricing guide for teams sizing DeepSeek chat and reasoning workloads.

GPT-4o Image Generation API

Compare costs before moving an OpenAI-style image workflow onto our API.

ChatGPT Image Generation API

Guide for turning manual image prompting into a repeatable API flow.

Image Generation API

Per-image pricing across every text-to-image model we serve.

Text to Video API

What a prompt-to-video clip costs, priced per second of output.

Voice Cloning API

Pricing for custom voice models and cloned speech generation.

Start Building in 5 Minutes

Get your API keys and start integrating AI features into your application immediately.

1

Get API Keys

Sign up and receive production API keys instantly

2

Choose SDK

Install our SDK for your language (Python, Node.js, Go, PHP)

3

Start Coding

Use our documentation and examples to integrate AI features

Stable Diffusion API pricing

A Stable Diffusion API call costs $0.0047 on the $47/month Standard plan (10,000 calls) and $0.0065 on the $21/month Basic plan (3,250 calls). On the $149/month Open Source Unlimited plan there is no per-image charge, which works out to about $0.0015 per image at 100,000 images a month.

Comparing providers? See how much Stable Diffusion costs through an API on ModelsLab, Stability AI, Replicate and fal, with prices checked September 27, 2026.

Model familymodel_idPer image (Standard)Unlimited planCatalogue
SDXLsdxl$0.0047Included, no per-image charge11,000+ SDXL checkpoints and LoRAs
Stable Diffusion 1.5any SD 1.5 model_id$0.0047Included, no per-image charge6,700+ SD 1.5 checkpoints
Fluxflux$0.0047Included, no per-image charge12,000+ Flux checkpoints and LoRAs. See Flux API pricing

Request details are on the Stable Diffusion API page. For a side-by-side with other providers, see the image API price comparison.

Developer Platform Features

Platform Capabilities

Production-ready infrastructure built for developers. REST APIs, WebSocket support, comprehensive SDKs, and enterprise-grade security – everything you need to ship AI features fast.

99.9% Uptime Guarantee

99.9% uptime SLA with redundant infrastructure across multiple regions

  • Multi-region deployment
  • Automatic failover
  • Load balancing
  • 24/7 monitoring

SDKs for Node.js, Python, Go & PHP

Production-ready SDKs with comprehensive documentation and code examples

  • RESTful APIs
  • WebSocket support
  • TypeScript definitions
  • Postman collections

Encryption & Access Controls

Encrypted in transit and at rest, with per-key access control

  • Data encryption
  • API key management
  • GDPR compliant
  • Data deletion on request

Auto-scaling GPU Capacity

Capacity scales with demand, with per-plan concurrency limits

  • Auto-scaling
  • Rate limiting
  • Usage analytics
  • Custom quotas

REST + WebSocket, Terraform Modules

Easy integration with popular frameworks and platforms

  • Webhook support
  • CI/CD integration
  • Docker images
  • Cloud deployment

Developer-First Technical Support

24/7 engineering support with deep technical expertise

  • Discord/Slack integration
  • Code-level assistance
  • API optimization help
  • Production troubleshooting
What You Get

One API Key, Every Modality

Image, video, audio, 3D and LLM endpoints behind a single account, billed per call.

Five modalities, one account

Text-to-image, image editing, text-to-video, video editing, speech, music, text-to-3D and LLM chat all share the same API key and wallet.

  • Image & image editing
  • Video & video editing
  • Speech, music & sound effects
  • Text-to-3D and LLM chat

Published SDKs

Install the client for your language, or copy a ready-made request straight out of any model’s playground.

  • pip install modelslab
  • npm install modelslab
  • Examples in cURL, Go & PHP
  • Per-model playground snippets

Built for async work

Video and 3D jobs run for minutes. Pass a webhook URL and we POST the result when the job finishes — no polling loop required.

  • Webhook callbacks on completion
  • Fetch-result endpoint for polling
  • Per-plan concurrency limits
  • Usage visible in the dashboard

Plans start at $21/month. Every plan reaches every model — you are never gated to a subset.

Ready to Code AI Features?

Get production API keys instantly. Start integrating AI into your codebase today with our developer-first platform designed for serious engineers.

Instant API Keys
Production-ready in 60 seconds
Complete SDKs
Python, Node.js, Go, PHP ready
Enterprise Infrastructure
99.9% uptime, auto-scaling
Get Production API Keys View API Documentation

Start coding immediately • Plans from $21/month • Scale when ready