FriendliAI
FriendliAI is an AI inference cloud that runs generative AI models fast, affordably, and reliably at scale. Its Friendli Suite spans three products: Model APIs (serverless, pay-per-token access to popular open-weight LLMs and multimodal models), Dedicated Endpoints (any open-source or custom model on dedicated GPUs with autoscaling, versioning, multi-LoRA and speculative decoding), and Friendli Container (self-hosted inference with gRPC, quantization and policy search). The API is OpenAI-compatible, so existing OpenAI applications migrate by changing the base URL and API key, with support for chat completions, tool calling, structured outputs, reasoning, audio transcription, embeddings and image generation. FriendliAI is a portfolio company of Sierra Ventures.
Real signal across most facets with visible, nameable gaps — the contract exists but is thin, or the portal is good while governance and commercial terms are absent.
API Evangelist profiles FriendliAI the way a machine reads it — 42 machine-readable artifacts across 33 APIs, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.
Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — FriendliAI scores 59.1/100 (developing), with a separate agent-readiness read of 72/100 (agent native). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.
Kin Score
This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.
Kin Score
How this is scored →scored 2026-07-27 · rubric v0.5
How we profile FriendliAI
Each block below is one kind of artifact we hold for FriendliAI. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.
APIs 33
Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.
Individual APIs this provider publishes, each with its own machine-readable definition.
FriendliAI Container.Audio API
The Container.Audio API from FriendliAI — 2 operation(s) for container.audio.
FriendliAI Container.Chat API
The Container.Chat API from FriendliAI — 2 operation(s) for container.chat.
FriendliAI Container.Classification API
The Container.Classification API from FriendliAI — 1 operation(s) for container.classification.
FriendliAI Container.Completions API
The Container.Completions API from FriendliAI — 2 operation(s) for container.completions.
FriendliAI Container.Image API
The Container.Image API from FriendliAI — 2 operation(s) for container.image.
FriendliAI Container.Messages API
The Container.Messages API from FriendliAI — 2 operation(s) for container.messages.
FriendliAI Container.Responses API
The Container.Responses API from FriendliAI — 2 operation(s) for container.responses.
FriendliAI Container.Token API
The Container.Token API from FriendliAI — 2 operation(s) for container.token.
FriendliAI Cost API
The Cost API from FriendliAI — 1 operation(s) for cost.
FriendliAI Dataset API
The Dataset API from FriendliAI — 8 operation(s) for dataset.
FriendliAI Dedicated.Audio API
The Dedicated.Audio API from FriendliAI — 2 operation(s) for dedicated.audio.
FriendliAI Dedicated.Chat API
The Dedicated.Chat API from FriendliAI — 2 operation(s) for dedicated.chat.
FriendliAI Dedicated.ChatRender API
The Dedicated.ChatRender API from FriendliAI — 1 operation(s) for dedicated.chatrender.
FriendliAI Dedicated.Classification API
The Dedicated.Classification API from FriendliAI — 1 operation(s) for dedicated.classification.
FriendliAI Dedicated.Completions API
The Dedicated.Completions API from FriendliAI — 2 operation(s) for dedicated.completions.
FriendliAI Dedicated.Embeddings API
The Dedicated.Embeddings API from FriendliAI — 1 operation(s) for dedicated.embeddings.
FriendliAI Dedicated.Endpoint API
The Dedicated.Endpoint API from FriendliAI — 9 operation(s) for dedicated.endpoint.
FriendliAI Dedicated.Image API
The Dedicated.Image API from FriendliAI — 2 operation(s) for dedicated.image.
FriendliAI Dedicated.Messages API
The Dedicated.Messages API from FriendliAI — 2 operation(s) for dedicated.messages.
FriendliAI Dedicated.Responses API
The Dedicated.Responses API from FriendliAI — 2 operation(s) for dedicated.responses.
FriendliAI Dedicated.Token API
The Dedicated.Token API from FriendliAI — 2 operation(s) for dedicated.token.
FriendliAI File API
The File API from FriendliAI — 3 operation(s) for file.
FriendliAI Serverless.Audio API
The Serverless.Audio API from FriendliAI — 2 operation(s) for serverless.audio.
FriendliAI Serverless.Chat API
The Serverless.Chat API from FriendliAI — 2 operation(s) for serverless.chat.
FriendliAI Serverless.ChatRender API
The Serverless.ChatRender API from FriendliAI — 1 operation(s) for serverless.chatrender.
FriendliAI Serverless.Completions API
The Serverless.Completions API from FriendliAI — 2 operation(s) for serverless.completions.
FriendliAI Serverless.Knowledge API
The Serverless.Knowledge API from FriendliAI — 1 operation(s) for serverless.knowledge.
FriendliAI Serverless.Messages API
The Serverless.Messages API from FriendliAI — 2 operation(s) for serverless.messages.
FriendliAI Serverless.Model API
The Serverless.Model API from FriendliAI — 2 operation(s) for serverless.model.
FriendliAI Serverless.Responses API
The Serverless.Responses API from FriendliAI — 2 operation(s) for serverless.responses.
FriendliAI Serverless.Token API
The Serverless.Token API from FriendliAI — 2 operation(s) for serverless.token.
FriendliAI Serverless.ToolAssistedChat API
The Serverless.ToolAssistedChat API from FriendliAI — 2 operation(s) for serverless.toolassistedchat.
FriendliAI Usage API
The Usage API from FriendliAI — 1 operation(s) for usage.
Scroll within the panel for all 33 ·
Arazzo Workflows 3
Real integrations are rarely a single call. Arazzo describes the multi-step sequences — auth, then create, then confirm — so both a human and an agent can follow the choreography, not just the endpoints.
Multi-step API workflows described with the Arazzo specification.
_Index
ARAZZOFriendliAI deploy a Dedicated Endpoint and infer
Create a Dedicated Endpoint, wait for it to be ready, then run a chat completion.
ARAZZOMCP Servers 1
Model Context Protocol servers expose these APIs directly to AI agents. We profile them because agent-native access is the fastest-growing way this provider's capabilities actually get used.
Model Context Protocol servers that expose these APIs to AI agents.
friendliai-mcp.yml
MCP SERVERRate Limits 1
Rate limits are the difference between a demo that works and a production integration that doesn't fall over. Publishing them is an operational-transparency signal — and a hard requirement for any agent that plans its own throughput.
Documented rate limits and quota policies.
Friendliai Rate Limits
RATE LIMITSSecurity Posture 3
Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Agentic Access 1
An x-agentic-access contract marks which operations are safe for an agent to run on its own and which need a human in the loop. It is the difference between an API an agent can use and one it can use safely.
Recommended x-agentic-access execution contracts for AI agents.
Resources
Every other property we hold for FriendliAI — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.
Get Started 4
Portal, sign-up, and the first successful call
Documentation 2
Reference material describing how the API behaves
Agent Surfaces 4
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 7
Pagination, idempotency, versioning, errors, and events
Scroll within the panel for all 7 ·
Build 4
SDKs, sample code, and the tooling you integrate with
Access & Security 3
Authentication, authorization, and security posture
Operate 5
Status, limits, changes, and where to get help
Commercial 3
Pricing, plans, and the legal terms of use
Company 2
The organization behind the API
Other 1
Properties that don't map to a standard resource type
← All providers · Data indexed from github.com/api-evangelist/friendliai · machine-readable index on apis.io