Replicate
Free tierRun open-source AI models in the cloud via a simple API — images, video, audio, and LLMs.
Free tier available·Technical·Powered by Multi-provider (Black Forest Labs, OpenAI, Google, Anthropic, ByteDance, xAI, Alibaba, Recraft, Minimax, and community models)·API available·Open source
Key strengths
Run thousands of community and official AI models via APIFine-tune models with custom dataDeploy custom models using Cog (open-source packaging tool)Automatic scaling up and down to zeroPay-per-use pricing with no idle charges for public modelsWide model variety: image, video, speech, music, LLMs
Free tier + paid plans
San Francisco, US
Founded 2021
Facts verified against replicate.com on
Recent changes
- Plans updated: Pay-per-use: public models billed by time (e.g. CPU $0.000100/sec, Nvidia T4 $0.000225/sec, Nvidia L40S $0.000975/sec, Nvidia A100 80GB $0.001400/sec) or by input/output (e.g. flux-1.1-pro $0.04/image, deepseek-r1 $0.01/1K output tokens). Private models billed for all online time including idle.
- Models updated: Multi-provider (Black Forest Labs, OpenAI, Google, Anthropic, ByteDance, xAI, Alibaba, Recraft, Minimax, and community models)
Get alerts when Replicate changes
Free. We'll email you when pricing, the free tier, API access or open-source status changes.
No ratings yet
- Rapid model prototyping: Query hundreds of open-source and commercial models (LLMs, image generators, video models) via a single unified API without provisioning GPU infrastructure
- Fine-tuning pipelines: Use Replicate's fine-tuning API to adapt supported models to custom datasets, then serve the fine-tuned version immediately
- Custom model deployment: Package proprietary models with Cog, push to Replicate, and expose them as scalable API endpoints with automatic scale-to-zero
- Cost-optimized inference: Leverage per-second or per-token billing to avoid over-provisioning; public model deployments incur zero cost at idle
- Multi-modal applications: Combine image (e.g., flux-1.1-pro), LLM (e.g., deepseek-r1), speech, music, and video models within a single application using consistent API patterns across providers including Google, Anthropic, xAI, Alibaba, and others
Alternatives
See all alternatives