Unlimited Open Source Models

Get Plan
Skip to main content
Open Source Unlimited Plan

Unlimited AI API for Open-Source Models

$149/month for unlimited generations on every open-source model ModelsLab hosts itself: Flux, SDXL, SD 1.5, Qwen Image, Wan 2.2, LTX 2.3, text to speech and all community LoRAs, with 15 parallel requests. Third-party models such as Kling, Seedance, Veo and hosted LLMs are billed per call from your wallet.

Last updated · By ModelsLab Engineering

15 Parallel Generations for lightning-fast results
Auto-scaling infrastructure that grows with your needs
Full access to all APIs and endpoints
Priority processing and dedicated support
🎨
Text to Image
Unlimited
🎬
Text to Video
Unlimited
🎵
Text to Audio
Unlimited
🖌️
Image Editing
Unlimited
🎲
Text to 3D
Unlimited
💬
LLM
Billed per token
15x Parallel Processing
ACTIVE
Auto-scaling enabled

What the Unlimited plan includes, and what it does not

Unlimited covers every model ModelsLab runs on its own GPUs: no call limit and no per-generation charge, 15 requests in parallel. Models from third-party providers (Kling, Seedance, Veo, Google, OpenAI, ElevenLabs and the hosted LLMs) are billed per call from your wallet on this plan, which includes no third-party usage. Counts are live public models.

Models included in the Open Source Unlimited plan versus models billed per call
CategoryIncluded (unlimited)Not included (billed per call)
Image29,347 modelse.g. sdxl, Flux.2 Dev Text to Image, Hidream-o1-text2img, Krea-2-turbo Text to Image, Qwen Image Edit 250942 modelse.g. Seedream 4.0 Image to image, Seedream 5.0 Lite Text To Image, Grok Imagine Image 2.0 Image Editing, Grok Imagine Image 2.0 Text To Image, Nano banana Text To Image
Video5 modelse.g. SVD, wan2.1, LTX 2.3, wan 2.2, CogVideoX92 modelse.g. Hailuo 2.3 Text To Video, Seedance 2.0 Mini — Text to Video, Gemini Omni — Video Edit, Grok Imagine Image To Video, MiniMax H3 Text to Video
Audio and voice12 models + 1,066 voicese.g. voice changer, sfx, ai music generator, speech to text, lyrics generator11 modelse.g. eleven_multilingual_v2, Elevenlabs Voice Changer, Inworld Text to Speech, song inpaint, Lyria 3
3D2 modelse.g. Image to 3D, Text to 3D0 models
LLM0 models364 modelse.g. Gemini 2.5 Pro, Z.ai: GLM 5.3, Qwen: Qwen3 235B A22B Instruct 2507, Qwen: Qwen3 VL 30B A3B Instruct, Qwen: Qwen3 14B

Image counts include community Flux, SDXL and SD 1.5 checkpoints and LoRAs. The plan includes no wallet credit, so fund a wallet before you call a third-party model. Compare every plan on the pricing page or see per-image costs on the cheapest AI image API page. For image, video and speech prices side by side, see Cheapest AI API.

Unlimited LLM API: what the $149 plan covers

Most LLM tokens are not unlimited on this plan. Nearly the whole LLM catalogue runs on partner providers, so chat completions are billed per million tokens from your wallet at the rate on each model page. The few self-hosted LLMs counted in the table above, and a few zero-priced community variants, carry no token charge for Unlimited subscribers.

The endpoint is OpenAI-compatible: point the OpenAI SDK at https://modelslab.com/api/v7/llm and use the same API key as your image, video and audio calls.

Trusted by Thousands of Premium Users

Join a thriving community of creators, developers, and businesses who have unlocked the full potential of AI with our unlimited plans.

5K+
Active Premium Users
Creators and businesses trust our platform
1.0M+
Generations Created per day
Total AI generations by our premium users
$250K+
Cost Savings
Saved by users switching to unlimited plans
120+
Countries Served
Global reach across all continents
"Switching to the unlimited plan was a game changer for our creative workflow. We've generated over 100K images this month without worrying about costs or limits."
User avatar
Sarah Chen
Creative Director, TechFlow Studio

Ready to join them and unlock unlimited AI generation?

🚀 Cancel any time
💳 No setup fees
⚡ Instant activation

Premium Features That Scale With You

Experience the full power of our AI platform with features designed for professionals and enterprises who demand the best.

15 Parallel Generations

Process multiple requests simultaneously for lightning-fast results and maximum productivity.

Auto-Scaling Infrastructure

Our intelligent system automatically scales resources based on demand, ensuring optimal performance.

Full API Access

Unlimited access to all our internal APIs and Endpoints

Priority Processing

Skip the queue with priority processing for all your AI generation requests.

High-Performance GPUs

Access to premium GPU infrastructure including RTX 4090s, A100s and H100 for faster inference.

99.9% Uptime Guarantee

Enterprise-grade reliability with guaranteed uptime and redundant infrastructure.

Team Collaboration

Share access with your team members and collaborate on AI projects seamlessly.

Dedicated Support

Get priority support from our expert team with direct access to engineers.

Ready to experience unlimited AI generation?

Join thousands of creators, developers, and businesses who trust our platform for their AI needs.

Starting at
$149/month
All open-source models
Unlimited generations

All Open-Source Models Included with Unlimited Access

Every open-source model we host on our own GPUs, across image, video and speech. No per-generation charge; up to 15 generations run in parallel.

ModelsLabPopular

Wan2.2 Image To Video

Open Source Model
ModelsLabPopular

Voice cloning

Open Source Model
ModelsLabPopular

Text to Speech

Open Source Model

Interior

Open Source Model

Ghibli Art Style

Open Source Model

Image Upscaler

Open Source Model

SDXL Headshot

Open Source Model

Plus Many More Models Being Added Weekly

Our team continuously adds new state-of-the-art models to keep you at the forefront of AI technology.

Choose Your Unlimited Plan

Start with unlimited access to all our open-source AI models

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
Testimonials

Trusted by Enterprise Teams Worldwide

Enterprise Success Stories

“

ModelsLab's Voice Cloning API has revolutionized how we approach character development in our games. It's like having a studio full of voice actors at our fingertips!

Alex Rivera
AR

Alex Rivera

Game Developer at TVC

“

The ease of creating lifelike voiceovers for our e-learning courses has dramatically increased engagement. A real breakthrough for educational content!

Priya Singh
PS

Priya Singh

Instructional Designer at TVC1

“

The LLM Chat API has dramatically helped me in how I approach chat integration. It's like giving an AI voice to my application, making it truly engaging. Thanks, ModelsLab!

John H.
JH

John H.

Developer Enthusiast at Mr

“

Voice Cloning from ModelsLab gave our marketing campaigns a unique edge with custom, realistic voiceovers. It's incredibly easy to use and effective.

Michael Chen
MC

Michael Chen

Digital Marketing Manager at TVC2

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 self-hosted open-source models: there is no call limit and no per-generation charge on them. The limit is concurrency: 15 requests can run at once, and a 16th is refused with a rate-limit error until a slot frees. Hourly rate limits also apply and are published on the rate limits page. Third-party models are not unlimited; they are billed per call from your wallet.

Every model ModelsLab hosts itself: 30,000+ community Flux, SDXL and SD 1.5 checkpoints and LoRAs, plus hosted models such as Flux.2 Dev, Qwen Image, Z-Image Turbo, Wan 2.1, Wan 2.2, LTX 2.3, MiniMax H3, text to speech, voice cloning, speech to text and image to 3D. The table on this page shows the live count per category.

Only the self-hosted ones: Wan 2.1, Wan 2.2, LTX 2.3, CogVideoX, SVD and the MiniMax H3 text-to-video, reference-to-video and start-end-frame models. Kling, Seedance, Veo, Runway, Vidu and the other third-party video models (about 90) are billed per call from wallet balance, and so is MiniMax H3 Fast reference-to-video.

Not as unlimited tokens. The LLM catalogue (364 models) runs on partner providers and is billed per million tokens from wallet balance. A few zero-priced community LLM variants carry no token charge on this plan.

15 parallel generations on Open Source Unlimited, against 10 on Standard and 5 on Basic. A request above the limit is refused with a rate-limit error, so retry it when one of your running jobs finishes.

Only for third-party models. The $149 plan includes no wallet credit, so Google, Kling, Seedance and LLM calls need a funded wallet. Open-source generation never draws on the wallet.

No. ModelsLab is paid-only. Each model page shows sample outputs and the exact request body, and the refund policy at modelslab.com/refund-policy applies to the plan.

Yes. Open Source Unlimited is billed monthly ($149) or yearly ($1,500), and you can cancel from the billing page at any time.
Plugins

Explore Plugins for Pro

Our plugins are designed to work with the most popular content creation software.

API

Build Apps with
ML
API

Use our API to build apps, generate AI art, create videos, and produce audio with ease.