Poolside

Poolside is an AI foundation model lab (founded 2023 by former GitHub CTO Jason Warner and Eiso Kant) building open-weight foundation models - the Laguna family - purpose-built for agentic software engineering. Poolside does not run a shared public SaaS API the way OpenAI or Groq do. Instead it publishes a full, public API reference (docs.poolside.ai) for an OpenAI-compatible inference API plus an admin/identity API, but the API itself only comes alive once a customer has a provisioned Poolside deployment - into their own AWS/Azure/Google Cloud VPC, on customer-owned NVIDIA GPU clusters via Helm, or fully air-gapped on-prem. There is no public signup page, free tier, or published pricing; access is arranged directly with Poolside's sales team. Separately, Poolside's smaller open-weight model, Laguna XS 2.1, can be called by anyone through third-party inference hosts such as OpenRouter, which is the closest thing to a public, self-serve way to hit a Poolside model over HTTP.

Poolside publishes 2 APIs on the APIs.io network: chat API and models API. Tagged areas include Artificial Intelligence, LLM, Foundation Models, Agentic Coding, and Software Engineering.

Poolside’s developer surface includes authentication, documentation, engineering blog, and 9 more developer resources.

🌐 Visit website 📡 Source on GitHub
37.0/100 thin ▬ flat Agent 26/100 agent aware saas Full breakdown ↓
scored 2026-09-14 · rubric v0.22.0
AccessEnterprise
1 APIs
Artificial IntelligenceLLMFoundation ModelsAgentic CodingSoftware EngineeringEnterpriseOn-PremOpen Weights

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-09-14 · rubric v0.22.0
Composite quality — 37.0/100 · thin
Contract Quality 10.9 / 23
Developer Ergonomics 4.3 / 18
Access Clarity 8.5 / 18
Operational Transparency 4.0 / 12
Contract Governance 0.0 / 11
Discoverability 6.2 / 9
Create-or-Update Ergonomics 0.0 / 10
Agent readiness — 26/100 · agent aware
Machine-Readable Contract 18 / 18
Agentic Access Contract 10 / 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
Create-or-Update Ergonomics applies to this provider. This API accepts writes, so it carries 10 points of the composite. It is scored from the published contracts themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in front of it, and the first time that check is skipped a duplicate record is created. Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet, not penalised by it.
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 github.com/api-evangelist/poolside-ai: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

Standards implemented 2

Interfaces this provider implements that became standards by being copied rather than ratified. Each is profiled by the API Commons, and the evidence column says how the claim was established — not that it was made.

The OpenAI Interface reaches extended
declared — publishes a spec that declares them
2 core of 338 operations graded · api-commons/models
SCIM 2.0
prose — states compatibility; nothing published to check it against
5 core of 24 operations graded · api-commons/identity

APIs 4

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

Poolside Identity Management API

Poolside's own admin API (/poolside/v1) for automating user and team administration on a deployment - create/get/update/delete users, and add, remove, or replace team membership...

Poolside SCIM API

SCIM 2.0 provisioning endpoint (/scim) for connecting an external identity provider (Okta, Entra ID, etc.) to automatically provision and deprovision Poolside users on a deploym...

Poolside chat API

The chat API from Poolside — 2 operation(s) for chat.

Poolside models API

The models API from Poolside — 1 operation(s) for models.

Open Collections 3

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

API Collection

OPEN COLLECTION

OpenAI Compatible chat API

OPEN COLLECTION

OpenAI Compatible chat models API

OPEN COLLECTION

Pricing Plans 1

Published pricing tiers and plan structures.

Poolside Ai Plans Pricing

3 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Poolside Ai Rate Limits

3 limits

RATE LIMITS

FinOps 1

Cost, billing, and metering signals for API financial operations.

Poolside Ai Finops

FINOPS

Security Posture 3

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

Poolside Ai Authentication

http · 1 scheme

SECURITY

Poolside Ai Vulnerability Disclosure

security.txt · contact published

SECURITY

Poolside Ai Trust Center

SOC 2, ISO 27001

SECURITY

Agentic Access 1

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

Poolside Ai Agentic Access

3 operations · 2 acting

3 operations · 2 acting

AGENTIC

Resources

Documentation 1

Reference material describing how the API behaves

Documentation
Documentation

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

AgenticAccess
AgenticAccess

Build 1

SDKs, sample code, and the tooling you integrate with

GitHubOrganization
GitHubOrganization

Access & Security 3

Authentication, authorization, and security posture

TrustCenter
TrustCenter
 VulnerabilityDisclosure
VulnerabilityDisclosure
 Authentication
Authentication

Operate 1

Status, limits, changes, and where to get help

RateLimits
RateLimits

Commercial 2

Pricing, plans, and the legal terms of use

Plans
Plans
 FinOps
FinOps

Company 3

The organization behind the API

LinkedIn
LinkedIn
 Website
Website
 Blog
Blog

Source (apis.yml)

apis.yml Raw ↑ 
aid: poolside-ai
url: https://raw.githubusercontent.com/api-evangelist/poolside-ai/refs/heads/main/apis.yml
name: Poolside
kind: company
description: Poolside is an AI foundation model lab (founded 2023 by former GitHub CTO Jason Warner and Eiso Kant) building
  open-weight foundation models - the Laguna family - purpose-built for agentic software engineering. Poolside does not run
  a shared public SaaS API the way OpenAI or Groq do. Instead it publishes a full, public API reference (docs.poolside.ai)
  for an OpenAI-compatible inference API plus an admin/identity API, but the API itself only comes alive once a customer has
  a provisioned Poolside deployment - into their own AWS/Azure/Google Cloud VPC, on customer-owned NVIDIA GPU clusters via
  Helm, or fully air-gapped on-prem. There is no public signup page, free tier, or published pricing; access is arranged directly
  with Poolside's sales team. Separately, Poolside's smaller open-weight model, Laguna XS 2.1, can be called by anyone through
  third-party inference hosts such as OpenRouter, which is the closest thing to a public, self-serve way to hit a Poolside
  model over HTTP.
deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: false
  label: Hosted service · you call their endpoint
  confidence: medium
  source:
  - openapi
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: enterprise
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Enterprise
  confidence: medium
  source:
  - plans
  - authentication
  - security
  generated: '2026-09-03'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/poolside-ai.png
tags:
- Artificial Intelligence
- LLM
- Foundation Models
- Agentic Coding
- Software Engineering
- Enterprise
- On-Prem
- Open Weights
tags_raw:
- AI
- LLM
- Foundation Models
- Agentic Coding
- Software Engineering
- Enterprise
- On-Prem
- Open Weights
created: '2026-07-02'
modified: '2026-07-02'
specificationVersion: '0.23'
apis:
- aid: poolside-ai:poolside-identity-management-api
  name: Poolside Identity Management API
  tags:
  - Admin
  - Team
  - User
  - Identity
  tags_raw:
  - Admin
  - Teams
  - Users
  - Identity
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.poolside.ai/organization/identity-management-api
  baseURL: https://<api-domain>/poolside/v1
  properties:
  - url: https://docs.poolside.ai/organization/identity-management-api
    type: Documentation
  - url: https://docs.poolside.ai/poolside-api/team/list-teams
    type: APIReference
  - url: https://docs.poolside.ai/poolside-api/team/add-team-members
    type: APIReference
  - url: https://docs.poolside.ai/poolside-api/user/create-user
    type: APIReference
  description: Poolside's own admin API (/poolside/v1) for automating user and team administration on a deployment - create/get/update/delete
    users, and add, remove, or replace team membership - as an alternative or complement to SCIM. Requires a service account
    API key created by a tenant-admin.
- aid: poolside-ai:poolside-scim-api
  name: Poolside SCIM API
  tags:
  - SCIM
  - Identity
  - Provisioning
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.poolside.ai/api/overview
  baseURL: https://<api-domain>/scim
  properties:
  - url: https://docs.poolside.ai/api/overview
    type: Documentation
  description: SCIM 2.0 provisioning endpoint (/scim) for connecting an external identity provider (Okta, Entra ID, etc.)
    to automatically provision and deprovision Poolside users on a deployment.
- aid: poolside-ai:poolside-ai-chat-api
  name: Poolside chat API
  description: The chat API from Poolside — 2 operation(s) for chat.
  humanURL: https://docs.poolside.ai/openai-api/chat/create-chat-completion
  baseURL: https://<api-domain>/openai/v1
  tags:
  - Chat
  tags_raw:
  - chat
  properties:
  - type: OpenAPI
    url: openapi/poolside-ai-chat-api-openapi.yml
  - type: Documentation
    url: https://docs.poolside.ai/api/overview
  - type: APIReference
    url: https://docs.poolside.ai/openai-api/chat/create-chat-completion
  - type: Documentation
    url: https://docs.poolside.ai/api/openai-api-examples
  - type: APIReference
    url: https://docs.poolside.ai/openai-api/chat/create-completion
  - type: APIReference
    url: https://docs.poolside.ai/openai-api/models/list-models
- aid: poolside-ai:poolside-ai-models-api
  name: Poolside models API
  description: The models API from Poolside — 1 operation(s) for models.
  humanURL: https://docs.poolside.ai/openai-api/chat/create-chat-completion
  baseURL: https://<api-domain>/openai/v1
  tags:
  - Models
  tags_raw:
  - models
  properties:
  - type: OpenAPI
    url: openapi/poolside-ai-models-api-openapi.yml
  - type: Documentation
    url: https://docs.poolside.ai/api/overview
  - type: APIReference
    url: https://docs.poolside.ai/openai-api/chat/create-chat-completion
  - type: Documentation
    url: https://docs.poolside.ai/api/openai-api-examples
  - type: APIReference
    url: https://docs.poolside.ai/openai-api/chat/create-completion
  - type: APIReference
    url: https://docs.poolside.ai/openai-api/models/list-models
common:
- type: AgenticAccess
  url: agentic-access/poolside-ai-agentic-access.yml
- type: TrustCenter
  url: security/poolside-ai-trust-center.yml
- type: VulnerabilityDisclosure
  url: security/poolside-ai-vulnerability-disclosure.yml
- type: Authentication
  url: authentication/poolside-ai-authentication.yml
- type: GitHubOrganization
  url: https://github.com/poolsideai
- type: LinkedIn
  url: https://www.linkedin.com/company/poolsideai
- type: Website
  url: https://poolside.ai/
- type: Documentation
  url: https://docs.poolside.ai/
- type: Plans
  url: plans/poolside-ai-plans-pricing.yml
- type: RateLimits
  url: rate-limits/poolside-ai-rate-limits.yml
- type: FinOps
  url: finops/poolside-ai-finops.yml
- url: https://poolside.ai/blog
  type: Blog
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com

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/poolside-ai"
All providers 
curl "https://apis.io/api/v1/providers?limit=25"
Every operation they expose 
curl "https://apis.io/api/v1/providers/poolside-ai/operations?limit=25"
How their score was established 
curl "https://apis.io/api/v1/providers/poolside-ai/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

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.