What it is

A catalog of thousands of community and official models — image, video, audio, LLM — each behind one prediction API. It is an inference host: you push a Cog container or run someone else's, and billing is per second of GPU time or per generated output.

Why it earns a slot

The fastest way to call a weird open model — a niche upscaler, a voice clone, a brand-new video model — without touching CUDA. Public models cost nothing when idle, so hobby projects sit at $0.

Know before you commit

Private and dedicated models bill for boot and idle time, not just inference — a deployment left running overnight can cost more than a month of API calls. Cold starts on rare models take minutes.

Getting started

pip install replicate (or npm i replicate)

Field notes

0 from the community

Sign in to add a field note. Reading is always open.

Loading notes…

Field check

Unverified

Sign in to confirm this entry is still accurate.

Pricing snapshot

Per second of compute (T4 $0.000225/s, A100 80GB $0.0014/s) or per output for media models (FLUX Dev $0.025/image, video from $0.09/s). Some LLMs bill per token. No free plan.

Snapshots move fast — verify at checkout, and post a field note if it changed.

Drop into your Lovable chat

Evaluate Replicate (https://replicate.com) for this project, then use it only if it fits what we are already building.
Context: Per-run model hosting API. A catalog of thousands of community and official models — image, video, audio, LLM — each behind one prediction API. It is an inference host: you push a Cog container or run someone else's, and billing is per second of GPU time or per generated output.
Reviewer notes (general, not written for this codebase): The fastest way to call a weird open model — a niche upscaler, a voice clone, a brand-new video model — without touching CUDA. Public models cost nothing when idle, so hobby projects sit at $0.
Watch out for: Private and dedicated models bill for boot and idle time, not just inference — a deployment left running overnight can cost more than a month of API calls. Cold starts on rare models take minutes.
Pricing: Per second of compute (T4 $0.000225/s, A100 80GB $0.0014/s) or per output for media models (FLUX Dev $0.025/image, video from $0.09/s). Some LLMs bill per token. No free plan.
Setup: pip install replicate (or npm i replicate)
Rules: treat the notes above as background only. Do not assume a theme, style, layout or feature that is not already in this project — inspect the existing code first and ask me before changing visual direction.

/api/public/tools/replicate

Also in Model APIs, routers & observability

Anthropic API / Claude Platform

platform.claude.com

Frontier model provider API

PaidModel APIs, routers & observability

Per token. Opus 5 $5/$25 per M in/out; Sonnet 5 $2/$10; Haiku 4.5 $1/$5; Fable 5 and Mythos 5 $10/$50. Batch API 50% off; cache reads 0.1x input.

Open dossier

Braintrust

braintrust.dev

LLM eval and experiment platform

Free tier + paidModel APIs, routers & observability

Starter free ($10/mo model credits, 1GB data, 10k scores, 14-day retention), Pro $249/mo ($249 credits, 5GB, 50k scores), Enterprise custom. Overage $3-4/GB and $1.50-$2.50 per 1k scores.

Open dossier

Fal.ai

fal.ai

Generative media inference host

PaidModel APIs, routers & observability

Per output or per second for media models: images ~$0.02-$0.04 at 1MP, video $0.05-$0.40 per second. Serverless GPU rates $1.10-$8.50/hr with committed-use discounts.

Open dossier

Fireworks AI

fireworks.ai

Open-model inference host

Free tier + paidModel APIs, routers & observability

Per token serverless across Standard/Priority/Fast tiers; embeddings $0.008-$0.10/M. On-demand GPUs billed per second: H100/H200 ~$7-8/hr, B200 ~$10-13/hr. Fine-tuning $0.50-$40 per M training tokens. $1 free credit.

Open dossier