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, AI, 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
53.1/100 developing ▬ flat Agent 62/100 agent native Full breakdown ↓
scored 2026-08-17 · rubric v0.11.0
AccessSelf serve
5 APIs 1 MCP Servers
CompanyAIMachine LearningLLMInferenceAgentsOpen Source ModelsInfrastructureDeveloper Tools

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-08-17 · rubric v0.11.0
Composite quality — 53.1/100 · developing
Contract Quality 17.1 / 25
Developer Ergonomics 14.2 / 20
Commercial Clarity 8.4 / 20
Operational Transparency 3.8 / 13
Governance 1.4 / 12
Discoverability 8.2 / 10
Agent readiness — 62/100 · agent native
Machine-Readable Contract 18 / 18
Agentic Access Contract 10 / 10
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
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/sail: 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 5

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

Sail Batches API API

Submit and manage batches of requests.

Sail Chat Completions API API

OpenAI-compatible Chat Completions API endpoints.

Sail Messages API API

Anthropic-compatible Messages API endpoints.

Sail Models API API

Model discovery endpoints.

Sail Responses API API

OpenAI-compatible Responses API endpoints.

Open Collections 6

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

API Collection

OPEN COLLECTION

Sail Batches API API

OPEN COLLECTION

Sail Batches API Chat Completions API API

OPEN COLLECTION

Sail Batches API Messages API API

OPEN COLLECTION

Sail Batches API Models API API

OPEN COLLECTION

Sail Batches API Responses API API

OPEN COLLECTION

MCP Servers 1

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

sail-mcp.yml

MCP SERVER

Event Specifications 1

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

Sail Webhooks

ASYNCAPI

Security Posture 2

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

Sail Authentication

http · 1 scheme

SECURITY

Sail Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Agentic Access 1

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

Sail Agentic Access

10 operations · 5 acting

10 operations · 5 acting

AGENTIC

Resources

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
AgenticAccess
 MCPServer
MCPServer
 LLMsTxt
LLMsTxt
 AgentSkill
AgentSkill

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Conventions
Conventions
 Idempotency
Idempotency
 Lifecycle
Lifecycle
 Conformance
Conformance
 Webhooks
Webhooks

Build 4

SDKs, sample code, and the tooling you integrate with

GitHubOrganization
GitHubOrganization
 Packages
Packages
 SDKs
SDKs
 CLI
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)

apis.yml Raw ↑ 
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
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: '2026-07-21'
image: https://sailresearch.com/og-image.png
tags:
- 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