RightNow AI

RightNow AI (RunInfra) turns plain-English descriptions of an inference workload into production, OpenAI-compatible AI endpoints. The platform selects open-source models from Hugging Face, benchmarks GPU options, applies kernel optimizations (quantization, speculative decoding, KV-cache tuning, Forge kernels), and deploys serverless, pay-per-token inference APIs on RunInfra Cloud, RunPod, Modal, or self-hosted GPUs. Its REST API is OpenAI-shaped and covers chat completions, responses, embeddings, rerank, image generation, audio speech and transcription, and model listing. A Y Combinator-backed research lab, RightNow AI also publishes open-source GPU-kernel and inference tooling.

RightNow AI publishes 7 APIs on the APIs.io network, including Audio API, Chat API, Embeddings API, and 4 more. Tagged areas include Company, Artificial Intelligence, Machine Learning, LLM Inference, and GPU.

RightNow AI’s developer surface includes documentation, API reference, getting-started guide, quickstart, signup flow, pricing, engineering blog, and 25 more developer resources.

🌐 Visit website 📡 Source on GitHub
54.8/100 developing ▬ flat Agent 29/100 agent aware Full breakdown ↓
scored 2026-08-17 · rubric v0.11.0
AccessSelf serve
7 APIs 1 MCP Servers
CompanyArtificial IntelligenceMachine LearningLLM InferenceGPUModel DeploymentServerlessOpenAI CompatibleEmbeddingsMLOps

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-08-17 · rubric v0.11.0
Composite quality — 54.8/100 · developing
Contract Quality 15.7 / 25
Developer Ergonomics 10.3 / 20
Commercial Clarity 12.1 / 20
Operational Transparency 7.2 / 13
Governance 1.4 / 12
Discoverability 8.2 / 10
Agent readiness — 29/100 · agent aware
Machine-Readable Contract 18 / 18
Agentic Access Contract 0 / 10
MCP Server 12 / 12
Machine-Readable Auth 0 / 10
Idempotency 0 / 9
Stable Error Semantics 0 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 7 / 7
Typed Event Surface 0 / 6
Agent Skills 5 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 3 / 3
A2A Agent Card 0 / 8
Dry-Run / Simulate Mode 0 / 4
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/rightnow: 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 7

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

RightNow AI Audio API

The Audio API from RightNow AI — 2 operation(s) for audio.

RightNow AI Chat API

The Chat API from RightNow AI — 1 operation(s) for chat.

RightNow AI Embeddings API

The Embeddings API from RightNow AI — 1 operation(s) for embeddings.

RightNow AI Images API

The Images API from RightNow AI — 1 operation(s) for images.

RightNow AI Models API

The Models API from RightNow AI — 2 operation(s) for models.

RightNow AI Rerank API

The Rerank API from RightNow AI — 1 operation(s) for rerank.

RightNow AI Responses API

The Responses API from RightNow AI — 1 operation(s) for responses.

Scroll for all 7

Open Collections 8

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

API Collection

OPEN COLLECTION

RunInfra Audio API

OPEN COLLECTION

RunInfra Audio Chat API

OPEN COLLECTION

RunInfra Audio Embeddings API

OPEN COLLECTION

RunInfra Audio Images API

OPEN COLLECTION

RunInfra Audio Models API

OPEN COLLECTION

RunInfra Audio Rerank API

OPEN COLLECTION

RunInfra Audio Responses API

OPEN COLLECTION

Scroll for all 8

MCP Servers 1

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

rightnow-mcp.yml

MCP SERVER

Security Posture 4

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

Rightnow Authentication

http · 1 scheme

SECURITY

Rightnow Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Rightnow Vulnerability Disclosure

security.txt · contact published

SECURITY

Rightnow Trust Center

SOC 2, HIPAA, GDPR

SECURITY

Resources

Get Started 5

Portal, sign-up, and the first successful call

DeveloperPortal
DeveloperPortal
 GettingStarted
GettingStarted
 Quickstart
Quickstart
 SignUp
SignUp
 Login
Login

Documentation 2

Reference material describing how the API behaves

Documentation
Documentation
 APIReference
APIReference

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

AgentSkill
AgentSkill
 MCPServer
MCPServer
 LLMsTxt
LLMsTxt
 WellKnown
WellKnown

Design & Contract 2

Pagination, idempotency, versioning, errors, and events

Conformance
Conformance
 Lifecycle
Lifecycle

Build 3

SDKs, sample code, and the tooling you integrate with

GitHubOrganization
GitHubOrganization
 SDKs
SDKs
 Packages
Packages

Access & Security 5

Authentication, authorization, and security posture

TrustCenter
TrustCenter
 DomainSecurity
DomainSecurity
 SecurityTxt
SecurityTxt
 Compliance
Compliance
 Security
Security

Operate 4

Status, limits, changes, and where to get help

Support
Support
 StatusPage
StatusPage
 Deprecation
Deprecation
 ChangeLog
ChangeLog

Commercial 3

Pricing, plans, and the legal terms of use

Pricing
Pricing
 TermsOfService
TermsOfService
 PrivacyPolicy
PrivacyPolicy

Company 3

The organization behind the API

Blog
Blog
 Twitter
Twitter
 LinkedIn
LinkedIn

Other 1

Properties that don't map to a standard resource type

Overlay
Overlay

Source (apis.yml)

apis.yml Raw ↑ 
aid: rightnow
name: RightNow AI
description: RightNow AI (RunInfra) turns plain-English descriptions of an inference workload into production, OpenAI-compatible
  AI endpoints. The platform selects open-source models from Hugging Face, benchmarks GPU options, applies kernel optimizations
  (quantization, speculative decoding, KV-cache tuning, Forge kernels), and deploys serverless, pay-per-token inference APIs
  on RunInfra Cloud, RunPod, Modal, or self-hosted GPUs. Its REST API is OpenAI-shaped and covers chat completions, responses,
  embeddings, rerank, image generation, audio speech and transcription, and model listing. A Y Combinator-backed research
  lab, RightNow AI also publishes open-source GPU-kernel and inference tooling.
url: https://raw.githubusercontent.com/api-evangelist/rightnow/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- y-combinator
tags:
- Company
- Artificial Intelligence
- Machine Learning
- LLM Inference
- GPU
- Model Deployment
- Serverless
- OpenAI Compatible
- Embeddings
- MLOps
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
image: https://runinfra.ai/favicon.ico
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-21'
x-enrichment:
  date: '2026-07-21'
  status: enriched
  artifacts_added: 21
  pass: local-v1
apis:
- aid: rightnow:rightnow-audio-api
  name: RightNow AI Audio API
  description: The Audio API from RightNow AI — 2 operation(s) for audio.
  humanURL: https://runinfra.ai/docs/api-reference/introduction
  baseURL: https://api.runinfra.ai/v1
  tags:
  - Audio
  properties:
  - type: OpenAPI
    url: openapi/rightnow-audio-api-openapi.yml
  - type: Authentication
    url: authentication/rightnow-authentication.yml
  - type: ErrorCatalog
    url: errors/rightnow-problem-types.yml
  - type: Conventions
    url: conventions/rightnow-conventions.yml
  - type: Idempotency
    url: conventions/rightnow-conventions.yml
  - type: DataModel
    url: data-model/rightnow-data-model.yml
- aid: rightnow:rightnow-chat-api
  name: RightNow AI Chat API
  description: The Chat API from RightNow AI — 1 operation(s) for chat.
  humanURL: https://runinfra.ai/docs/api-reference/introduction
  baseURL: https://api.runinfra.ai/v1
  tags:
  - Chat
  properties:
  - type: OpenAPI
    url: openapi/rightnow-chat-api-openapi.yml
  - type: Authentication
    url: authentication/rightnow-authentication.yml
  - type: ErrorCatalog
    url: errors/rightnow-problem-types.yml
  - type: Conventions
    url: conventions/rightnow-conventions.yml
  - type: Idempotency
    url: conventions/rightnow-conventions.yml
  - type: DataModel
    url: data-model/rightnow-data-model.yml
- aid: rightnow:rightnow-embeddings-api
  name: RightNow AI Embeddings API
  description: The Embeddings API from RightNow AI — 1 operation(s) for embeddings.
  humanURL: https://runinfra.ai/docs/api-reference/introduction
  baseURL: https://api.runinfra.ai/v1
  tags:
  - Embeddings
  properties:
  - type: OpenAPI
    url: openapi/rightnow-embeddings-api-openapi.yml
  - type: Authentication
    url: authentication/rightnow-authentication.yml
  - type: ErrorCatalog
    url: errors/rightnow-problem-types.yml
  - type: Conventions
    url: conventions/rightnow-conventions.yml
  - type: Idempotency
    url: conventions/rightnow-conventions.yml
  - type: DataModel
    url: data-model/rightnow-data-model.yml
- aid: rightnow:rightnow-images-api
  name: RightNow AI Images API
  description: The Images API from RightNow AI — 1 operation(s) for images.
  humanURL: https://runinfra.ai/docs/api-reference/introduction
  baseURL: https://api.runinfra.ai/v1
  tags:
  - Images
  properties:
  - type: OpenAPI
    url: openapi/rightnow-images-api-openapi.yml
  - type: Authentication
    url: authentication/rightnow-authentication.yml
  - type: ErrorCatalog
    url: errors/rightnow-problem-types.yml
  - type: Conventions
    url: conventions/rightnow-conventions.yml
  - type: Idempotency
    url: conventions/rightnow-conventions.yml
  - type: DataModel
    url: data-model/rightnow-data-model.yml
- aid: rightnow:rightnow-models-api
  name: RightNow AI Models API
  description: The Models API from RightNow AI — 2 operation(s) for models.
  humanURL: https://runinfra.ai/docs/api-reference/introduction
  baseURL: https://api.runinfra.ai/v1
  tags:
  - Models
  properties:
  - type: OpenAPI
    url: openapi/rightnow-models-api-openapi.yml
  - type: Authentication
    url: authentication/rightnow-authentication.yml
  - type: ErrorCatalog
    url: errors/rightnow-problem-types.yml
  - type: Conventions
    url: conventions/rightnow-conventions.yml
  - type: Idempotency
    url: conventions/rightnow-conventions.yml
  - type: DataModel
    url: data-model/rightnow-data-model.yml
- aid: rightnow:rightnow-rerank-api
  name: RightNow AI Rerank API
  description: The Rerank API from RightNow AI — 1 operation(s) for rerank.
  humanURL: https://runinfra.ai/docs/api-reference/introduction
  baseURL: https://api.runinfra.ai/v1
  tags:
  - Rerank
  properties:
  - type: OpenAPI
    url: openapi/rightnow-rerank-api-openapi.yml
  - type: Authentication
    url: authentication/rightnow-authentication.yml
  - type: ErrorCatalog
    url: errors/rightnow-problem-types.yml
  - type: Conventions
    url: conventions/rightnow-conventions.yml
  - type: Idempotency
    url: conventions/rightnow-conventions.yml
  - type: DataModel
    url: data-model/rightnow-data-model.yml
- aid: rightnow:rightnow-responses-api
  name: RightNow AI Responses API
  description: The Responses API from RightNow AI — 1 operation(s) for responses.
  humanURL: https://runinfra.ai/docs/api-reference/introduction
  baseURL: https://api.runinfra.ai/v1
  tags:
  - Responses
  properties:
  - type: OpenAPI
    url: openapi/rightnow-responses-api-openapi.yml
  - type: Authentication
    url: authentication/rightnow-authentication.yml
  - type: ErrorCatalog
    url: errors/rightnow-problem-types.yml
  - type: Conventions
    url: conventions/rightnow-conventions.yml
  - type: Idempotency
    url: conventions/rightnow-conventions.yml
  - type: DataModel
    url: data-model/rightnow-data-model.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: AgentSkill
  url: skills/rightnow-audio-transcription.md
- type: MCPServer
  url: mcp/rightnow-mcp.yml
- type: Overlay
  url: overlays/rightnow-runinfra-overlay.yaml
- type: TrustCenter
  url: security/rightnow-trust-center.yml
- type: DomainSecurity
  url: security/rightnow-domain-security.yml
- type: DeveloperPortal
  url: https://runinfra.ai/docs
- type: Documentation
  url: https://runinfra.ai/docs
- type: APIReference
  url: https://runinfra.ai/docs/api-reference/introduction
- type: GettingStarted
  url: https://runinfra.ai/docs/introduction/quickstart
- type: Quickstart
  url: https://runinfra.ai/docs/introduction/quickstart
- type: SignUp
  url: https://runinfra.ai/sign-up
- type: Login
  url: https://runinfra.ai/sign-in
- type: Pricing
  url: https://runinfra.ai/pricing
- type: Blog
  url: https://runinfra.ai/news
- type: GitHubOrganization
  url: https://github.com/RightNow-AI
- type: Support
  url: https://runinfra.ai/contact
- type: TermsOfService
  url: https://runinfra.ai/terms-of-service
- type: PrivacyPolicy
  url: https://runinfra.ai/privacy-policy
- type: StatusPage
  url: https://status.runinfra.ai/
- type: Twitter
  url: https://x.com/runinfrai
- type: LinkedIn
  url: https://www.linkedin.com/showcase/runinfra/
- type: LLMsTxt
  url: llms/rightnow-llms.txt
- type: WellKnown
  url: well-known/rightnow-well-known.yml
- type: SecurityTxt
  url: well-known/rightnow-security.txt
- type: SDKs
  url: packages/rightnow-packages.yml
- type: Packages
  url: packages/rightnow-packages.yml
- type: Conformance
  url: conformance/rightnow-conformance.yml
- type: Lifecycle
  url: lifecycle/rightnow-lifecycle.yml
- type: Deprecation
  url: lifecycle/rightnow-lifecycle.yml
- type: ChangeLog
  url: changelog/rightnow-changelog.yml
- type: Compliance
  url: conformance/rightnow-conformance.yml
- type: Security
  url: security/rightnow-vulnerability-disclosure.yml