FriendliAI
Inference cloud for open-weight and custom models, with 99.99% uptime SLAs and dedicated GPU endpoints.
Infrastructure by FriendliAI
IndexedLicense unknown
Get started
About
FriendliAI is an inference cloud for frontier open-weight and custom AI models. It offers Model APIs for popular open-weight models, Dedicated Endpoints for running any model on dedicated GPUs, and one-click deployment of Hugging Face models.
Use cases: model-inference
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Fact sheet
- Category
- Inference · api
- Self-host
- Yesfriendli.ai
- SLA
- 99.99% uptime SLAfriendli.ai
Plans
| Model APIs | Contact sales | per 1M tokens, e.g. GLM-5.3 from $1.26 input and $3.96 output after a 10% discount |
|---|---|---|
| Dedicated Endpoints | Contact sales | on-demand per GPU-hour billed per second, e.g. H100 80GB at $5.00 per hour |
| BYOG | Contact sales | run the Friendli inference stack on your own GPUs; contact sales |
From the vendor's pricing page, read Oct 24, 2026.
Facts read from the vendor's own pages by claude-haiku-5-5 on Oct 24, 2026; a fact is shown only with the page it came from.
Details
- License
- License unknown
- Website
- friendli.ai
- Docs
- friendli.ai/docs
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- WebsiteDocsPricing page
Cite this page
FriendliAI. Agent Mart. https://agentmart.dev/infrastructure/friendliai (last updated 2026-10-24)