Criterion OpenRouter Replicate
CategoryLLM APIs & Model PlatformsAI Deployment & Monitoring
In one sentenceOne OpenAI-compatible API key for hundreds of models from many providers.Run and deploy open-source and custom AI models through an API, paying per second of hardware or per output.
Problem it solvesManaging separate accounts, keys and SDKs for every model provider, and coping with provider outages.Using or deploying AI models, especially image and video models, without managing GPUs.
Free planYesNo
Developer APIYes — docsYes — docs
Open sourceNoNo
PlatformsWeb, REST APIWeb, REST API
Pricing (summary)No subscription: inference is billed at each provider's list price, with a platform fee of 5.5% (Standard) or 8% (Business) on credit purchases. A free plan offers 25+ free models with request caps; Enterprise is contract-based.
Checked 2026-10-19		Usage-based. Public models mostly bill by hardware time (e.g. Nvidia T4 $0.81/hr, A100 80GB $5.04/hr, H100 $5.49/hr, billed per second). Some official models bill per output or token, such as flux-1.1-pro at $0.04 per image.
Checked 2026-10-19
Strengths
  • Huge model catalogue
  • Provider list prices passed through
  • Free tier for testing
  • Simple pay-per-use pricing
  • Huge model selection
  • Good for media models
Limitations
  • 5.5% (Standard) or 8% (Business) fee on credit purchases
  • Free model caps are low
  • Another intermediary in the data path
  • No free tier mentioned on the pricing page
  • Private deployments bill idle time
  • Costs vary by model runtime and can be hard to predict