Kinference

Kinference (pronounced "kay-inference") is an open-source inference control plane for Kubernetes and vLLM, built by Buoyant, Inc. (the company behind Linkerd). It turns any GPU-enabled Kubernetes cluster into a distributed inference platform with a traffic gateway that accepts OpenAI and Anthropic inference APIs, per-tenant token rate limits, policy-driven model routing, KV cache-aware load balancing, semantic classification, model aliases, and Prometheus/Grafana metrics, configured declaratively through Kubernetes CRDs and the kinfctl CLI. A commercial Kinference Enterprise edition is offered by Buoyant.

Kinference is listed with 2 APIs on the APIs.io network. Tagged areas include Company, Inference, Kubernetes, vLLM, and LLM Gateway.

Kinference’s developer surface includes CLI, changelog, sandbox, authentication, documentation, API reference, getting-started guide, and 16 more developer resources.

🌐 Visit website 📡 Profile data on GitHub

30.8/100 thin Agent 8/100 agent aware Full breakdown ↓
scored 2026-11-06 · rubric v0.27.0 · Show this score on your site →

AccessEnterprise

2 APIs

Company Inference KubernetesvLLMLLM Gateway Rate Limiting Load Balancing Open Source Platform Engineering

Kin Score

Kin Score How this is scored →
scored 2026-11-06 · rubric v0.27.0

Composite quality — 30.8/100 · thin

Contract Quality 2.6 / 21

Developer Ergonomics 10.9 / 17

Access Clarity 3.6 / 17

Operational Transparency 2.3 / 11

Contract Governance 1.9 / 10

Discoverability 4.9 / 9

Regulatory Posture 2.3 / 15

Agent readiness — 8/100 · agent aware

Machine-Readable Contract 0 / 18

Agentic Access Contract 0 / 10

Documented Reversibility 0 / 6

MCP Server 0 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 8 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 7 / 7

Typed Event Surface 0 / 6

Agent Skills 0 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Well-Known Document 0 / 5

Pagination 5 / 5

Distinct Operations 3 / 3

MCP Tool Quality 6 / 6

Regulatory Posture applies to this provider. Its tags matched the Horizontal (data, software, accessibility, platform) regime, so Regulatory Posture carries 15 points of the composite. If this regime is wrong for your business, say so on your provider repo — the applicability map is public and we will correct it.

Create-or-Update Ergonomics could not be measured. We hold no machine-readable contract for this provider to read, so there is nothing to measure a write surface against. Excluded rather than scored zero: never-measured and measured-empty are different facts. Publishing an OpenAPI is what makes this facet — and several others — scorable at all.

The six quality facets above are damped to 85 points between them, because the conditional facet above carries the other 15. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 85% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.

Show this score on your site.

It updates itself when the score changes. Paste this where you link to your API docs:

<a href="https://apis.io/providers/kinference-ai/"><img src="https://apis.io/badge/kinference-ai/card.svg" alt="Kinference on APIs.io — Kin Score by API Evangelist"></a>

Other styles, a README pill and a shields.io endpoint are on the badge page.

Raise your score.

Agent readiness — checks not met, largest first (exact, from this profile):

Machine-Readable Contract +18 pts — api_specs includes an OpenAPI document
MCP Server +12 pts — deployment.mode + probe verdict on the mcp/ manifest, not the pointer; an unprobed slug falls back to authorship
Agentic Access Contract +10 pts — agentic_access artifact present (x-agentic-access), graded by author
Idempotency +9 pts — OpenAPI mutating operations declare an idempotency key — a header, a request-body property, or a named de-duplication token whose own description says so (verified); else common[].type matches /idempoten/i (documented)
A2A Agent Card +8 pts — a2a/-a2a.yml manifest, graded on conformance.grade against A2A 1.0.0
Request/Response Examples +7 pts — share of operations carrying request/response examples; else an Examples / Code Samples link

10 more unmet checks in the Agent Readiness table above.

Kin Score — facets with the most composite points still available (weight × headroom):

Contract Quality scores 12.0 — up to +22.0 composite points
Access Clarity scores 21.1 — up to +15.8 composite points
Operational Transparency scores 21.1 — up to +10.3 composite points

Each check links to what satisfies it. Publish the artifact, or tell us where it already lives, and the score moves on the next scoring run.

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from the provider profile at artifacts.apis.io/kinference-ai/apis.yml: open an issue on github.com/api-evangelist/kinference-ai to ask a question or point us at an artifact you publish. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

APIs 2

Individual APIs this provider publishes, each with its own machine-readable definition.

Kinference Picker gRPC API

The kinference.v1 Picker gRPC service used by the Kinference router - given an inference request it picks a model and destination (a local inference engine pod or an off-cluster...

Kinference Kubernetes CRD API

Kubernetes custom resources in the kinference.buoyant.io/v1alpha1 group (InferencePolicy, InferencePool, InferenceProvider, InferenceWorkerSet, plus GatewayBackend) used to decl...

Kinference API pricing

Prices published by Kinference.

Plan	Price
Buoyant AI	Talk to us

Plan details, limits and sources →

Pricing Plans 1

Published pricing tiers and plan structures.

Kinference Ai Plans Pricing

1 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Kinference Ai Rate Limits

0 limits

RATE LIMITS

JSON Schema 4

Standalone JSON Schema definitions for this provider's data models.

InferencePolicy (kinference.buoyant.io/v1alpha1)

5 properties

JSON SCHEMA

InferencePool (kinference.buoyant.io/v1alpha1)

5 properties

JSON SCHEMA

InferenceProvider (kinference.buoyant.io/v1alpha1)

5 properties

JSON SCHEMA

InferenceWorkerSet (kinference.buoyant.io/v1alpha1)

5 properties

JSON SCHEMA

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Kinference Ai Authentication

2 schemes

SECURITY

Kinference Ai Domain Security

TLSv1.3

SECURITY

Resources

Get Started 2

Portal, sign-up, and the first successful call

Sandbox

Sandbox

GettingStarted

GettingStarted

Documentation 2

Reference material describing how the API behaves

Documentation

Documentation

APIReference

APIReference

Design & Contract 4

Pagination, idempotency, versioning, errors, and events

Conventions

Lifecycle

ErrorCatalog

Conformance

Build 6

SDKs, sample code, and the tooling you integrate with

CLI

IntegrationEdges

SDKs

Packages

GitHubOrganization

GitHubOrganization

GitHubRepository

GitHubRepository

Access & Security 2

Authentication, authorization, and security posture

Authentication

Authentication

DomainSecurity

DomainSecurity

Operate 1

Status, limits, changes, and where to get help

ChangeLog

ChangeLog

Commercial 1

Pricing, plans, and the legal terms of use

Plans

Plans

Company 2

The organization behind the API

Website

Website

Blog

Blog

Other 3

Properties that don't map to a standard resource type

Hosts

Hosts

Vendors

Vendors

Enterprise

Enterprise

Source (apis.yml)

aid: kinference-ai
name: Kinference
description: Kinference (pronounced "kay-inference") is an open-source inference control plane for Kubernetes and vLLM, built
  by Buoyant, Inc. (the company behind Linkerd). It turns any GPU-enabled Kubernetes cluster into a distributed inference
  platform with a traffic gateway that accepts OpenAI and Anthropic inference APIs, per-tenant token rate limits, policy-driven
  model routing, KV cache-aware load balancing, semantic classification, model aliases, and Prometheus/Grafana metrics, configured
  declaratively through Kubernetes CRDs and the kinfctl CLI. A commercial Kinference Enterprise edition is offered by Buoyant.
url: https://artifacts.apis.io/kinference-ai/apis.yml
x-type: company
x-source: harvest:manual
x-tier: profiled
x-tier-reason: enrichment pass 2026-11-05 (modular-v1; was harvest)
accessModel:
  pricing: enterprise
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Enterprise
  confidence: high
  probe_state: covered
  source:
  - plans
  - authentication
  - security
  - sandbox
  generated: '2026-11-06'
  method: derived
specificationVersion: '0.20'
created: '2026-11-05'
modified: '2026-11-05'
tags:
- Company
- Inference
- Kubernetes
- vLLM
- LLM Gateway
- Rate Limiting
- Load Balancing
- Open Source
- Platform Engineering
tags_raw:
- Company
- AI Inference
- Kubernetes
- vLLM
- LLM Gateway
- Rate Limiting
- Load Balancing
- Open Source
- Platform Engineering
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
image: https://kinference.ai/images/kinference-opengraph.png
common:
- type: Plans
  url: plans/kinference-ai-plans-pricing.yml
- type: CLI
  url: cli/kinference-ai-cli.yml
- type: ChangeLog
  url: changelog/kinference-ai-changelog.yml
- type: Conventions
  url: conventions/kinference-ai-conventions.yml
- type: Sandbox
  url: sandbox/kinference-ai-sandbox.yml
- type: Authentication
  url: authentication/kinference-ai-authentication.yml
- type: Lifecycle
  url: lifecycle/kinference-ai-lifecycle.yml
- type: ErrorCatalog
  url: errors/kinference-ai-error-codes.yml
- type: Conformance
  url: conformance/kinference-ai-conformance.yml
- type: Hosts
  url: hosts/kinference-ai-hosts.yml
- type: IntegrationEdges
  url: integrations/kinference-ai-integration-edges.yml
- type: Vendors
  url: vendors/kinference-ai-vendors.yml
- type: SDKs
  url: packages/kinference-ai-packages.yml
- type: Packages
  url: packages/kinference-ai-packages.yml
- type: DomainSecurity
  url: security/kinference-ai-domain-security.yml
- type: Website
  url: https://kinference.ai/
- type: Documentation
  url: https://kinference.ai/docs/
- type: APIReference
  url: https://kinference.ai/docs/reference/
- type: GettingStarted
  url: https://kinference.ai/docs/getting-started/
- type: GitHubOrganization
  url: https://github.com/Kinference-AI
- type: GitHubRepository
  url: https://github.com/Kinference-AI/kinference
- type: Blog
  url: https://buoyant.io/tag/inference
- type: Enterprise
  url: https://www.buoyant.io/products/kinference-enterprise-buoyant-ai
apis:
- name: Kinference Picker gRPC API
  description: The kinference.v1 Picker gRPC service used by the Kinference router - given an inference request it picks a
    model and destination (a local inference engine pod or an off-cluster provider), with streaming PushBody/PullBody, Pick,
    ReportFirstToken, ReportFinalToken and Abort RPCs. Self-hosted inside the customer's Kubernetes cluster, so there is no
    public base URL. Contract published by Buoyant in the Kinference-AI/kinference repository.
  humanURL: https://kinference.ai/docs/reference/
  tags:
  - gRPC
  - Inference Routing
  properties:
  - type: Protobuf
    name: kinference.v1 Picker (proto)
    url: grpc/kinference-ai-router.proto
  - type: Protobuf
    name: Protobuf (provider-hosted)
    url: https://github.com/Kinference-AI/kinference/blob/main/crates/kinference-router/proto/kinference.proto
  - type: GitHubRepository
    url: https://github.com/Kinference-AI/kinference
  aid: kinference-ai:kinference-picker-grpc-api
- name: Kinference Kubernetes CRD API
  description: Kubernetes custom resources in the kinference.buoyant.io/v1alpha1 group (InferencePolicy, InferencePool, InferenceProvider,
    InferenceWorkerSet, plus GatewayBackend) used to declaratively configure the Kinference inference control plane; served
    by the customer's own Kubernetes API server.
  humanURL: https://kinference.ai/docs/reference/crds/
  tags:
  - Kubernetes
  - CRD
  properties:
  - type: JSONSchema
    name: InferencePolicy schema
    url: json-schema/kinference-ai-inferencepolicy-schema.json
  - type: JSONSchema
    name: InferencePool schema
    url: json-schema/kinference-ai-inferencepool-schema.json
  - type: JSONSchema
    name: InferenceProvider schema
    url: json-schema/kinference-ai-inferenceprovider-schema.json
  - type: JSONSchema
    name: InferenceWorkerSet schema
    url: json-schema/kinference-ai-inferenceworkerset-schema.json
  - type: APIReference
    url: https://kinference.ai/docs/reference/crds/
  aid: kinference-ai:kinference-kubernetes-crd-api
x-coverage:
  state: covered
  reason: identity-verified
  detail: Website kinference.ai serves title "Kinference" and footer "© 2026 Buoyant, Inc."; pointers taken from homepage
    nav/sitemap and verified live. No Terms/Privacy/Pricing/Support pages are linked from kinference.ai.
  evidence:
  - url: https://kinference.ai/
    status: 200
  - url: https://kinference.ai/docs/
    status: 200
  - url: https://kinference.ai/docs/reference/
    status: 200
  - url: https://kinference.ai/docs/getting-started/
    status: 200
  - url: https://github.com/Kinference-AI
    status: 200
  - url: https://github.com/Kinference-AI/kinference
    status: 200
  - url: https://buoyant.io/tag/inference
    status: 200
  - url: https://www.buoyant.io/products/kinference-enterprise-buoyant-ai
    status: 200
x-enrichment:
  date: '2026-11-05'
  status: enriched
  artifacts_added: 24
  pass: modular-v1
  engine: identity=anthropic,contract=anthropic,surfaces=anthropic,docs=anthropic,regulatory=anthropic

Kinference API — frequently asked questions

Does Kinference have an API?

Yes. APIs.io lists 2 APIs from Kinference, including Kinference Picker gRPC API and Kinference Kubernetes CRD API.

How do I authenticate with the Kinference API?

Kinference uses bearer-token authentication (2 schemes). The details are profiled on APIs.io as Kinference Ai Authentication.

How much does the Kinference API cost?

Kinference publishes its prices; its Buoyant AI plan is Talk to us as of 2026-11-05. APIs.io lists 1 pricing plan for Kinference, with each plan's price, limits and inclusions under Pricing on this page.

Is the Kinference API ready for AI agents?

Kinference has a Kin Score of 30.8 out of 100 (thin) and an Agent Readiness score of 7.9 (agent-aware), scored by API Evangelist on 2026-11-06.

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/kinference-ai"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/kinference-ai/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/kinference-ai/evidence"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.