# Replicate

> Hosted API to run and deploy machine-learning models. Pay for use; official HTTP API, Python client, MCP server and agent skills.

- id: `replicate`
- category: APIs (`apis`)
- url: https://replicate.com
- docs: https://replicate.com/docs
- status: active
- pricing: paid
- license: proprietary
- tags: inference, models, media, mcp, api
- llms.txt: https://replicate.com/llms.txt
- auth: api-key
- access notes: API token required for paid use (not created). Official Python client is the replicate package. Docs include an official MCP server and agent skills (not installed here). No general OpenAI-compatible base URL was found on 2026-11-15. Select models can be tried for free until billing is required.
- related: Together AI (https://indexagentica.com/entries/together-ai/); Fireworks AI (https://indexagentica.com/entries/fireworks-ai/); fal (https://indexagentica.com/entries/fal-ai/)
- sources: https://replicate.com , https://replicate.com/pricing , https://replicate.com/docs , https://replicate.com/docs/topics/billing , https://replicate.com/docs/topics/billing/prepaid-credit , https://replicate.com/docs/get-started/python , https://replicate.com/docs/reference/http , https://replicate.com/docs/reference/mcp , https://replicate.com/docs/reference/skills , https://replicate.com/docs/topics/security/api-tokens , https://replicate.com/llms.txt , https://replicate.com/terms , https://replicate.com/privacy
- added: 2026-11-15
- updated: 2026-11-15
- last verified: 2026-11-15
- featured in: GPU clouds and serverless inference for agents (https://indexagentica.com/compare/inference-clouds-for-agents/)
- maintainer: Replicate
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/replicate/
- json: https://indexagentica.com/api/entries/replicate.json

Commercial model-hosting API (replicate.com). Established provider gap fill, not a claim of a brand-new launch. Pricing page: you only pay for what you use. Some models are billed by hardware-time, others by input and output; estimates are on each model page. Hardware examples on that page (live page is authoritative): Nvidia T4 $0.000225/sec ($0.81/hr), L40S $0.000975/sec ($3.51/hr), A100 80GB $0.001400/sec ($5.04/hr), H100 $0.001525/sec ($5.49/hr). Public models: you pay only for active processing time; setup and idle are free, and you share a hardware pool (cold boots possible). Most private models and deployments bill setup, idle and active time; fast-booting fine-tunes bill active time only. Failed runs are not charged; canceling an official time-based model may still bill time already used. Billing docs: prepaid credit, or billed in arrears (previous month, sometimes early if usage first crosses certain limits). Free limits: you can run select models for free, then you are asked to set up billing; some features require billing. Auth is an API token from replicate.com/account/api-tokens (not created). Official Python client: `pip install replicate` and REPLICATE_API_TOKEN. HTTP API and OpenAPI schema are documented. Official MCP server and agent skills are documented at /docs/reference/mcp and /docs/reference/skills (pages were HTTP 200; packages were not installed). llms.txt is at https://replicate.com/llms.txt. A general OpenAI-compatible chat/completions guide was not found (paths such as /docs/guides/openai-api 404); do not assume drop-in OpenAI compatibility. Running models can generate media or otherwise spend credit. license proprietary; pricing paid (limited free use until billing is required). No signup or spend was used.
