Inference website screenshot

Inference

Inference (inference.net) is an AI infrastructure platform for AI-native teams. It offers an OpenAI-compatible inference API for open-source, frontier, and custom fine-tuned language models, alongside Catalyst — its observability, tracing, evaluation, training, and deployment platform. Developers call chat completions, batch/async inference, function calling, structured outputs, and vision endpoints at https://api.inference.net/v1 using a Bearer API key; route and monitor traffic through the Catalyst Gateway; fine-tune and deploy custom models; and optimize agents end to end with HALO. The platform ships a first-party CLI (inf), a hosted MCP server, and webhooks for asynchronous inference. Backed by Multicoin Capital.

Inference publishes 1 API on the APIs.io network. Tagged areas include Company, Artificial Intelligence, Machine Learning, LLM, and Inference.

The Inference catalog on APIs.io includes 1 event-driven AsyncAPI specification.

Inference’s developer surface includes documentation, API reference, getting-started guide, engineering blog, pricing, signup flow, authentication, and 18 more developer resources.

46.1/100 developing ▬ flat Agent 34/100 agent aware Full breakdown ↓
scored 2026-07-27 · rubric v0.5
AccessFreemiumSelf serve⚡ Free to try
1 APIs 1 MCP Servers
CompanyArtificial IntelligenceMachine LearningLLMInferenceObservabilityModel TrainingModel DeploymentMCPCrypto Web3

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 46.1/100 · developing
Contract Quality 5.7 / 25
Developer Ergonomics 12.6 / 20
Commercial Clarity 16.8 / 20
Operational Transparency 1.7 / 13
Governance 0.0 / 12
Discoverability 9.3 / 10
Agent readiness — 34/100 · agent aware
Machine-Readable Contract 0 / 18
Agentic Access Contract 0 / 15
MCP Server 12 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 0 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 7 / 7
Typed Event Surface 6 / 6
Agent Skills 0 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/inference: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 1

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

Inference.net API

OpenAI-compatible inference API for open-source, frontier, and custom language models — chat completions, batch/async inference, function calling, structured outputs, and vision...

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

inference-mcp.yml

MCP SERVER

Pricing Plans 1

Published pricing tiers and plan structures.

Inference Plans

3 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Inference Rate Limits

0 limits

RATE LIMITS

Event Specifications 1

AsyncAPI definitions for this provider's event-driven and streaming APIs.

Security Posture 2

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

Inference Authentication

apiKey · 1 scheme

SECURITY

Inference Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Resources

Get Started 4

Portal, sign-up, and the first successful call

Documentation 2

Reference material describing how the API behaves

Agent Surfaces 2

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 4

Pagination, idempotency, versioning, errors, and events

Build 3

SDKs, sample code, and the tooling you integrate with

Access & Security 3

Authentication, authorization, and security posture

Operate 1

Status, limits, changes, and where to get help

Commercial 4

Pricing, plans, and the legal terms of use

Company 2

The organization behind the API

Source (apis.yml)

apis.yml Raw ↑
aid: inference
name: Inference
description: Inference (inference.net) is an AI infrastructure platform for AI-native teams. It offers an OpenAI-compatible
  inference API for open-source, frontier, and custom fine-tuned language models, alongside Catalyst — its observability,
  tracing, evaluation, training, and deployment platform. Developers call chat completions, batch/async inference, function
  calling, structured outputs, and vision endpoints at https://api.inference.net/v1 using a Bearer API key; route and monitor
  traffic through the Catalyst Gateway; fine-tune and deploy custom models; and optimize agents end to end with HALO. The
  platform ships a first-party CLI (inf), a hosted MCP server, and webhooks for asynchronous inference. Backed by Multicoin
  Capital.
url: https://raw.githubusercontent.com/api-evangelist/inference/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- multicoin-capital
x-tier: profiled
x-tier-reason: enrichment-pipeline
accessModel:
  pricing: freemium
  onboarding: self-serve
  trial: false
  try_now: true
  public: false
  label: Freemium · Self-serve signup
  confidence: high
  source:
  - plans
  - authentication
  generated: '2026-07-22'
  method: derived
image: https://inference.net/og/home.png
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-19'
tags:
- Company
- Artificial Intelligence
- Machine Learning
- LLM
- Inference
- Observability
- Model Training
- Model Deployment
- MCP
- Crypto Web3
apis:
- name: Inference.net API
  description: OpenAI-compatible inference API for open-source, frontier, and custom language models — chat completions, batch/async
    inference, function calling, structured outputs, and vision — authenticated with a Bearer API key.
  humanURL: https://docs.inference.net/api/api-quickstart
  baseURL: https://api.inference.net/v1
  tags:
  - LLM
  - Inference
  - OpenAI Compatible
  properties:
  - type: Documentation
    url: https://docs.inference.net
  - type: APIReference
    url: https://docs.inference.net/api/api-quickstart
  - type: Authentication
    url: https://docs.inference.net/reference/api-keys
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: DomainSecurity
  url: security/inference-domain-security.yml
- type: Website
  url: https://inference.net
- type: DeveloperPortal
  url: https://docs.inference.net
- type: Documentation
  url: https://docs.inference.net
- type: APIReference
  url: https://docs.inference.net/api/api-quickstart
- type: GettingStarted
  url: https://docs.inference.net/api/api-quickstart
- type: Blog
  url: https://inference.net/blog
- type: Pricing
  url: https://inference.net/pricing
- type: SignUp
  url: https://inference.net/register
- type: Login
  url: https://inference.net/signin
- type: TermsOfService
  url: https://inference.net/terms-of-service
- type: PrivacyPolicy
  url: https://inference.net/privacy-policy
- type: GitHubOrganization
  url: https://github.com/context-labs
- type: TrustCenter
  url: https://trust.inference.net
- type: Authentication
  url: authentication/inference-authentication.yml
- type: RateLimits
  url: rate-limits/inference-rate-limits.yml
- type: Plans
  url: plans/inference-plans.yml
- type: MCPServer
  url: mcp/inference-mcp.yml
- type: CLI
  url: cli/inference-cli.yml
- type: Packages
  url: packages/inference-packages.yml
- type: Conventions
  url: conventions/inference-conventions.yml
- type: Lifecycle
  url: lifecycle/inference-lifecycle.yml
- type: Webhooks
  url: asyncapi/inference-webhooks.yml
- type: Conformance
  url: conformance/inference-conformance.yml
- type: LLMsTxt
  url: llms/inference-llms.txt
x-enrichment:
  date: '2026-07-19'
  status: backfilled
  pass: local-v1
  note: backfilled from .gitignore signal + verified work evidence