Recommended Models
The Try for Free collection is our list of models that you can run without purchasing credit after creating a Replicate account. This is great to see if Replicate will work for your use case before spending money.
No. The models in this collection are free for a limited number of runs. After you've hit the free use limit, you'll need to add billing and purchase credit to continue using these models.
Think about the type of task you want to test—like text-to-image generation, image restoration, or video creation—and select a model from the collection that matches it.
Popular options include google/imagen-4 and black-forest-labs/flux-1.1-pro. The goal is to experiment quickly and see what works for your use case.
This collection covers a wide range of capabilities, such as:
In many cases, yes—but it depends on the model’s license.
Even if a model is free to run, it may have restrictions on commercial use. Always review the license on the model card before using its outputs in a product or project.
Recommended Models

Google's Imagen 4 flagship model
Updated 1 week, 4 days ago
6.3M runs

A state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming images through natural language
Updated 3 weeks, 3 days ago
38.6M runs

Faster, better FLUX Pro. Text-to-image model with excellent image quality, prompt adherence, and output diversity.
Updated 3 weeks, 5 days ago
64.8M runs

ideogram-ai/ideogram-v3-turboTurbo is the fastest and cheapest Ideogram v3. v3 creates images with stunning realism, creative designs, and consistent styles
Updated 4 weeks, 1 day ago
5M runs

luma/reframe-videoChange the aspect ratio of any video up to 30 seconds long, outputs will be 720p
Updated 4 weeks, 1 day ago
25.1K runs

Generate 6s videos with prompts or images. (Also known as Hailuo). Use a subject reference to make a video with a character and the S2V-01 model.
Updated 4 weeks, 1 day ago
624.6K runs

A 12 billion parameter rectified flow transformer capable of generating images from text descriptions
Updated 5 months, 1 week ago
33.9M runs

Generate expressive, natural speech. Features unique emotion control, instant voice cloning from short audio, and built-in watermarking.
Updated 5 months, 2 weeks ago
181.8K runs

topazlabs/image-upscaleProfessional-grade image upscaling, from Topaz Labs
Updated 7 months, 1 week ago
1M runs

topazlabs/video-upscaleVideo Upscaling from Topaz Labs
Updated 7 months, 1 week ago
783.9K runs

sczhou/codeformerRobust face restoration algorithm for old photos / AI-generated faces
Updated 10 months, 2 weeks ago
46.8M runs

tencentarc/gfpganPractical face restoration algorithm for *old photos* or *AI-generated faces*
Updated 1 year, 8 months ago
102.7M runs