Sail

Sail Research provides cloud infrastructure for running long-horizon AI agents efficiently. Its inference platform serves leading open-source models (GLM, Kimi, DeepSeek, gpt-oss, Gemma, and more) through an OpenAI-compatible Responses and Chat Completions API plus an Anthropic-compatible Messages API, so existing SDKs work as drop-in clients. "Completion windows" (asap, priority, standard, flex) trade latency for 30-80% token savings, and a Batch API processes up to 100,000 requests asynchronously. Sailboxes add persistent virtual-machine compute for agents that need to run indefinitely, with checkpoint/resume, networking, and a native CLI. The platform supports LoRA fine-tunes, Tinker RL rollouts, prompt caching, completion webhooks, and usage/observability (Voyages) for background agents.

Sail publishes 5 APIs on the APIs.io network, including Batches API API, Chat Completions API API, Messages API API, and 2 more. Tagged areas include Company, Artificial Intelligence, Machine-Learning, LLM, and Inference.

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

Sail’s developer surface includes documentation, API reference, getting-started guide, pricing, signup flow, engineering blog, authentication, and 20 more developer resources.

🌐 Visit website 📡 Source on GitHub

46.9/100 developing ▬ flat Agent 43/100 agent native saas Full breakdown ↓
scored 2026-09-06 · rubric v0.19.0

1 APIs 1 MCP Servers

Company Artificial Intelligence Machine-Learning LLM Inference Agents Open Source Models Infrastructure Developer Tools

Kin Score

Kin Score How this is scored →
scored 2026-09-06 · rubric v0.19.0

Composite quality — 46.9/100 · developing

Contract Quality 15.8 / 25

Developer Ergonomics 13.7 / 20

Access Clarity 6.8 / 20

Operational Transparency 2.4 / 13

Contract Governance 0.5 / 12

Discoverability 7.6 / 10

Agent readiness — 43/100 · agent native

Machine-Readable Contract 18 / 18

Agentic Access Contract 10 / 10

Documented Reversibility 0 / 6

MCP Server 12 / 12

Machine-Readable Auth 10 / 10

Idempotency 9 / 9

Stable Error Semantics 8 / 8

Request/Response Examples 7 / 7

Rate-Limit Signaling 0 / 7

Typed Event Surface 6 / 6

Agent Skills 5 / 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

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/sail: 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 →

APIs 5

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

MCP Servers 1

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

Get Started 3

Portal, sign-up, and the first successful call

DeveloperPortal

DeveloperPortal

GettingStarted

GettingStarted

SignUp

SignUp

Documentation 2

Reference material describing how the API behaves

Documentation

Documentation

APIReference

APIReference

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

AgenticAccess

MCPServer

LLMsTxt

AgentSkill

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Conventions

Idempotency

Lifecycle

Conformance

Webhooks

Build 4

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

Packages

SDKs

CLI

Access & Security 3

Authentication, authorization, and security posture

TrustCenter

TrustCenter

Authentication

Authentication

DomainSecurity

DomainSecurity

Operate 1

Status, limits, changes, and where to get help

StatusPage

StatusPage

Commercial 2

Pricing, plans, and the legal terms of use

Pricing

Pricing

TermsOfService

TermsOfService

Company 2

The organization behind the API

Website

Website

Blog

Blog

Other 1

Properties that don't map to a standard resource type

Overlay

Overlay

Source (apis.yml)

aid: sail
name: Sail
description: Sail Research provides cloud infrastructure for running long-horizon AI agents efficiently. Its inference platform
  serves leading open-source models (GLM, Kimi, DeepSeek, gpt-oss, Gemma, and more) through an OpenAI-compatible Responses
  and Chat Completions API plus an Anthropic-compatible Messages API, so existing SDKs work as drop-in clients. "Completion
  windows" (asap, priority, standard, flex) trade latency for 30-80% token savings, and a Batch API processes up to 100,000
  requests asynchronously. Sailboxes add persistent virtual-machine compute for agents that need to run indefinitely, with
  checkpoint/resume, networking, and a native CLI. The platform supports LoRA fine-tunes, Tinker RL rollouts, prompt caching,
  completion webhooks, and usage/observability (Voyages) for background agents.
url: https://raw.githubusercontent.com/api-evangelist/sail/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- redpoint-ventures
x-tier: profiled
x-tier-reason: has-api-surface
deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: true
  label: Hosted service · you call their endpoint
  confidence: high
  source:
  - openapi
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: unknown
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Unknown
  confidence: low
  source:
  - authentication
  - security
  generated: '2026-09-03'
  method: derived
specificationVersion: '0.23'
created: '2026-07-17'
modified: '2026-07-21'
image: https://sailresearch.com/og-image.png
tags:
- Company
- Artificial Intelligence
- Machine-Learning
- LLM
- Inference
- Agents
- Open Source Models
- Infrastructure
- Developer Tools
tags_raw:
- Company
- AI
- Machine Learning
- LLM
- Inference
- Agents
- Open Source Models
- Infrastructure
- Developer Tools
apis:
- aid: sail:sail-batches-api-api
  name: Sail Batches API API
  description: Submit and manage batches of requests.
  humanURL: https://docs.sailresearch.com/api-reference/chat-completions-api/create-a-chat-completion
  baseURL: https://api.sailresearch.com/v1
  tags:
  - Batches API
  properties:
  - type: OpenAPI
    url: openapi/sail-batches-api-api-openapi.yml
  - type: ErrorCatalog
    url: errors/sail-problem-types.yml
  - type: DataModel
    url: data-model/sail-data-model.yml
- aid: sail:sail-chat-completions-api-api
  name: Sail Chat Completions API API
  description: OpenAI-compatible Chat Completions API endpoints.
  humanURL: https://docs.sailresearch.com/api-reference/chat-completions-api/create-a-chat-completion
  baseURL: https://api.sailresearch.com/v1
  tags:
  - Chat Completions API
  properties:
  - type: OpenAPI
    url: openapi/sail-chat-completions-api-api-openapi.yml
  - type: ErrorCatalog
    url: errors/sail-problem-types.yml
  - type: DataModel
    url: data-model/sail-data-model.yml
- aid: sail:sail-messages-api-api
  name: Sail Messages API API
  description: Anthropic-compatible Messages API endpoints.
  humanURL: https://docs.sailresearch.com/api-reference/chat-completions-api/create-a-chat-completion
  baseURL: https://api.sailresearch.com/v1
  tags:
  - Messages API
  properties:
  - type: OpenAPI
    url: openapi/sail-messages-api-api-openapi.yml
  - type: ErrorCatalog
    url: errors/sail-problem-types.yml
  - type: DataModel
    url: data-model/sail-data-model.yml
- aid: sail:sail-models-api-api
  name: Sail Models API API
  description: Model discovery endpoints.
  humanURL: https://docs.sailresearch.com/api-reference/chat-completions-api/create-a-chat-completion
  baseURL: https://api.sailresearch.com/v1
  tags:
  - Models API
  properties:
  - type: OpenAPI
    url: openapi/sail-models-api-api-openapi.yml
  - type: ErrorCatalog
    url: errors/sail-problem-types.yml
  - type: DataModel
    url: data-model/sail-data-model.yml
- aid: sail:sail-responses-api-api
  name: Sail Responses API API
  description: OpenAI-compatible Responses API endpoints.
  humanURL: https://docs.sailresearch.com/api-reference/chat-completions-api/create-a-chat-completion
  baseURL: https://api.sailresearch.com/v1
  tags:
  - Responses API
  properties:
  - type: OpenAPI
    url: openapi/sail-responses-api-api-openapi.yml
  - type: ErrorCatalog
    url: errors/sail-problem-types.yml
  - type: DataModel
    url: data-model/sail-data-model.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Overlay
  url: overlays/sail-openapi-overlay.yaml
- type: Website
  url: https://www.sailresearch.com/
- type: DeveloperPortal
  url: https://docs.sailresearch.com
- type: Documentation
  url: https://docs.sailresearch.com
- type: APIReference
  url: https://docs.sailresearch.com/api-reference/chat-completions-api/create-a-chat-completion
- type: GettingStarted
  url: https://docs.sailresearch.com/quickstart
- type: Pricing
  url: https://docs.sailresearch.com/pricing
- type: SignUp
  url: https://app.sailresearch.com
- type: Blog
  url: https://www.sailresearch.com/blog
- type: GitHubOrganization
  url: https://github.com/sailresearchco
- type: TrustCenter
  url: https://trust.sailresearch.com
- type: StatusPage
  url: https://status.sailresearch.com
- type: TermsOfService
  url: https://docs.sailresearch.com/dpa
- type: Authentication
  url: authentication/sail-authentication.yml
- type: AgenticAccess
  url: agentic-access/sail-agentic-access.yml
- type: DomainSecurity
  url: security/sail-domain-security.yml
- type: Conventions
  url: conventions/sail-conventions.yml
- type: Idempotency
  url: conventions/sail-conventions.yml
- type: Lifecycle
  url: lifecycle/sail-lifecycle.yml
- type: Conformance
  url: conformance/sail-conformance.yml
- type: Packages
  url: packages/sail-packages.yml
- type: SDKs
  url: packages/sail-packages.yml
- type: CLI
  url: cli/sail-cli.yml
- type: MCPServer
  url: mcp/sail-mcp.yml
- type: LLMsTxt
  url: llms/sail-llms.txt
- type: Webhooks
  url: asyncapi/sail-webhooks.yml
- type: AgentSkill
  url: skills/_index.yml
x-enrichment:
  date: '2026-07-21'
  status: enriched
  artifacts_added: 16
  pass: local-v1

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/sail"

All providers

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

Every operation they expose

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

How their score was established

curl "https://apis.io/api/v1/providers/sail/evidence"

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

Get an API key

Free tier, no email required.

GitHub Google LinkedIn

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