Nous Research

Nous Research is an AI research and infrastructure company ("The AI Accelerator Company") known for the open-weight Hermes family of language models (including Hermes 4) and for Nous Portal, an OpenAI-compatible inference API served at inference-api.nousresearch.com. The Portal aggregates Nous's own Hermes models alongside a broad catalog of open and frontier third-party models (OpenRouter- style routing, 280+ models) behind a single chat-completions endpoint. Distinctively, the inference API supports the x402 HTTP payment protocol, returning HTTP 402 with a Solana USDC micropayment envelope so agents can pay per request without a pre-provisioned account. Beyond inference, Nous ships the Hermes Agent framework, Atropos RL environments, and Psyche/DisTrO for distributed model training over the internet. Backed by Paradigm.

Nous Research publishes 2 APIs on the APIs.io network: Chat API and Models API. Tagged areas include Company, Ai, Machine Learning, Large Language Models, and Inference.

Nous Research’s developer surface includes authentication, documentation, API reference, signup flow, engineering blog, support, and 17 more developer resources.

38.5/100 thin ▬ flat Agent 65/100 agent native Full breakdown ↓
scored 2026-07-27 · rubric v0.5
AccessSelf serve
2 APIs 1 MCP Servers
CompanyAiMachine LearningLarge Language ModelsInferenceAgentsOpen Weightsx402

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 38.5/100 · thin
Contract Quality 14.6 / 25
Developer Ergonomics 11.3 / 20
Commercial Clarity 2.6 / 20
Operational Transparency 0.7 / 13
Governance 0.0 / 12
Discoverability 9.3 / 10
Agent readiness — 65/100 · agent native
Machine-Readable Contract 18 / 18
Agentic Access Contract 15 / 15
MCP Server 12 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 0 / 7
Typed Event Surface 0 / 6
Agent Skills 5 / 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/nous-research: 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 2

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

Nous Research Chat API

OpenAI-compatible chat completions.

Nous Research Models API

Model discovery and catalog.

MCP Servers 1

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

Security Posture 2

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

Nous Research Authentication

http · 1 scheme

SECURITY

Nous Research Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Agentic Access 1

Recommended x-agentic-access execution contracts for AI agents.

Nous Research Agentic Access

2 operations · 1 acting

2 operations · 1 acting

AGENTIC

Resources

Get Started 2

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 5

Pagination, idempotency, versioning, errors, and events

Build 1

SDKs, sample code, and the tooling you integrate with

Access & Security 2

Authentication, authorization, and security posture

Operate 1

Status, limits, changes, and where to get help

Company 4

The organization behind the API

Other 2

Properties that don't map to a standard resource type

Source (apis.yml)

apis.yml Raw ↑
aid: nous-research
name: Nous Research
description: Nous Research is an AI research and infrastructure company ("The AI Accelerator Company") known for the open-weight
  Hermes family of language models (including Hermes 4) and for Nous Portal, an OpenAI-compatible inference API served at
  inference-api.nousresearch.com. The Portal aggregates Nous's own Hermes models alongside a broad catalog of open and frontier
  third-party models (OpenRouter- style routing, 280+ models) behind a single chat-completions endpoint. Distinctively, the
  inference API supports the x402 HTTP payment protocol, returning HTTP 402 with a Solana USDC micropayment envelope so agents
  can pay per request without a pre-provisioned account. Beyond inference, Nous ships the Hermes Agent framework, Atropos
  RL environments, and Psyche/DisTrO for distributed model training over the internet. Backed by Paradigm.
url: https://raw.githubusercontent.com/api-evangelist/nous-research/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- paradigm
x-tier: active
x-tier-reason: has-public-api
accessModel:
  pricing: unknown
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Self-serve signup
  confidence: medium
  source:
  - authentication
  generated: '2026-07-22'
  method: derived
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-20'
image: https://nousresearch.com/wp-content/uploads/2024/03/android-chrome-512x512-1-300x300.png
tags:
- Company
- Ai
- Machine Learning
- Large Language Models
- Inference
- Agents
- Open Weights
- x402
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
apis:
- aid: nous-research:nous-research-chat-api
  name: Nous Research Chat API
  description: OpenAI-compatible chat completions.
  humanURL: https://portal.nousresearch.com/docs
  baseURL: https://inference-api.nousresearch.com/v1
  tags:
  - Chat
  properties:
  - type: OpenAPI
    url: openapi/nous-research-chat-api-openapi.yml
  - type: InterfaceLicense
    url: https://portal.nousresearch.com/docs
- aid: nous-research:nous-research-models-api
  name: Nous Research Models API
  description: Model discovery and catalog.
  humanURL: https://portal.nousresearch.com/docs
  baseURL: https://inference-api.nousresearch.com/v1
  tags:
  - Models
  properties:
  - type: OpenAPI
    url: openapi/nous-research-models-api-openapi.yml
  - type: InterfaceLicense
    url: https://portal.nousresearch.com/docs
common:
- type: AgenticAccess
  url: agentic-access/nous-research-agentic-access.yml
- type: MCPServer
  url: mcp/nous-research-mcp.yml
- type: AgentSkill
  url: skills/_index.yml
- type: LLMsTxt
  url: llms/nous-research-llms.txt
- type: Conventions
  url: conventions/nous-research-conventions.yml
- type: ErrorCatalog
  url: errors/nous-research-problem-types.yml
- type: Lifecycle
  url: lifecycle/nous-research-lifecycle.yml
- type: Conformance
  url: conformance/nous-research-conformance.yml
- type: DataModel
  url: data-model/nous-research-data-model.yml
- type: Overlay
  url: overlays/nous-research-inference-api-overlay.yaml
- type: DomainSecurity
  url: security/nous-research-domain-security.yml
- type: Authentication
  url: authentication/nous-research-authentication.yml
- type: Website
  url: https://nousresearch.com
- type: DeveloperPortal
  url: https://portal.nousresearch.com
- type: Documentation
  url: https://portal.nousresearch.com/docs
- type: APIReference
  url: https://portal.nousresearch.com/docs
- type: SignUp
  url: https://portal.nousresearch.com
- type: Blog
  url: https://nousresearch.com/blog
- type: GitHubOrganization
  url: https://github.com/NousResearch
- type: Support
  url: https://discord.gg/jqVphNsB4H
- type: HuggingFace
  url: https://huggingface.co/NousResearch
- type: Twitter
  url: https://twitter.com/nousresearch
- type: LinkedIn
  url: https://www.linkedin.com/company/nousresearch/
x-enrichment:
  date: '2026-07-20'
  status: enriched
  artifacts_added: 16
  pass: local-v1