Asterlab

Aster (Aster AI Labs, PBC), operating as Asterlab, is a San Francisco based Y Combinator (Spring 2026) public benefit corporation building autonomous research systems that coordinate thousands of AI research agents working in parallel to automate open-ended scientific discovery. The company used that same autonomous-research system to optimize its own inference stack and now offers Aster Inference, an OpenAI-compatible inference API serving open-weight models (gpt-oss-120b, gpt-oss-120b-fast, and Z.ai's GLM 5.2) at what it benchmarks as the fastest gpt-oss-120b output speed on GPU (644 tok/s). The API works with the official OpenAI Python and JS SDKs, LangChain, LiteLLM, Cursor, the Vercel AI SDK, and most agent frameworks by pointing the base URL at https://api.asterlab.ai/v1, with zero data retention by default.

Asterlab publishes 1 API on the APIs.io network. Tagged areas include Company, Artificial Intelligence, Machine Learning, LLM, and Inference.

Asterlab’s developer surface includes documentation, getting-started guide, pricing, signup flow, engineering blog, support, authentication, and 7 more developer resources.

🌐 Visit website 📡 Source on GitHub

27.3/100 emerging ▬ flat Agent 14/100 human only Full breakdown ↓
scored 2026-07-28 · rubric v0.5

AccessSelf serve

1 APIs

CompanyArtificial IntelligenceMachine LearningLLMInferenceOpenAI CompatibleAutonomous ResearchGPUDeveloper Tools

Kin Score

Kin Score How this is scored →
scored 2026-07-28 · rubric v0.5

Composite quality — 27.3/100 · emerging

Contract Quality 0.0 / 25

Developer Ergonomics 9.1 / 20

Commercial Clarity 8.9 / 20

Operational Transparency 0.0 / 13

Governance 0.0 / 12

Discoverability 9.3 / 10

Agent readiness — 14/100 · human only

Machine-Readable Contract 0 / 18

Agentic Access Contract 0 / 15

MCP Server 0 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 0 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 0 / 7

Typed Event Surface 0 / 6

Agent Skills 0 / 5

Well-Known Catalog 4 / 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/asterlab: 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 1

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

Get Started 3

Portal, sign-up, and the first successful call

DeveloperPortal

DeveloperPortal

GettingStarted

GettingStarted

SignUp

SignUp

Documentation 1

Reference material describing how the API behaves

Documentation

Documentation

Agent Surfaces 2

MCP servers, agent skills, and machine-readable catalogs

WellKnown

WellKnown

LLMsTxt

LLMsTxt

Design & Contract 1

Pagination, idempotency, versioning, errors, and events

Conventions

Conventions

Access & Security 2

Authentication, authorization, and security posture

Authentication

Authentication

DomainSecurity

DomainSecurity

Operate 1

Status, limits, changes, and where to get help

Support

Support

Commercial 3

Pricing, plans, and the legal terms of use

Pricing

Pricing

TermsOfService

TermsOfService

PrivacyPolicy

PrivacyPolicy

Company 1

The organization behind the API

Blog

Blog

Source (apis.yml)

aid: asterlab
name: Asterlab
description: Aster (Aster AI Labs, PBC), operating as Asterlab, is a San Francisco based Y Combinator (Spring 2026) public
  benefit corporation building autonomous research systems that coordinate thousands of AI research agents working in parallel
  to automate open-ended scientific discovery. The company used that same autonomous-research system to optimize its own inference
  stack and now offers Aster Inference, an OpenAI-compatible inference API serving open-weight models (gpt-oss-120b, gpt-oss-120b-fast,
  and Z.ai's GLM 5.2) at what it benchmarks as the fastest gpt-oss-120b output speed on GPU (644 tok/s). The API works with
  the official OpenAI Python and JS SDKs, LangChain, LiteLLM, Cursor, the Vercel AI SDK, and most agent frameworks by pointing
  the base URL at https://api.asterlab.ai/v1, with zero data retention by default.
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://www.asterlab.ai/og/default.png
url: https://raw.githubusercontent.com/api-evangelist/asterlab/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- y-combinator
x-tier: stub
x-tier-reason: portfolio-lead
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-18'
tags:
- Company
- Artificial Intelligence
- Machine Learning
- LLM
- Inference
- OpenAI Compatible
- Autonomous Research
- GPU
- Developer Tools
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
apis:
- name: Aster Inference API
  description: OpenAI-compatible inference API from Aster serving open-weight models (gpt-oss-120b, gpt-oss-120b-fast, GLM
    5.2). Authenticate with an Aster API key created in the inference console and set the base URL to https://api.asterlab.ai/v1;
    works with the OpenAI SDKs, LangChain, LiteLLM, and most agent frameworks. Zero data retention by default.
  humanURL: https://www.asterlab.ai/inference
  baseURL: https://api.asterlab.ai/v1
  tags:
  - Inference
  - LLM
  - OpenAI Compatible
  properties:
  - type: Authentication
    url: authentication/asterlab-authentication.yml
  - type: Conventions
    url: conventions/asterlab-conventions.yml
common:
- type: DeveloperPortal
  url: https://www.asterlab.ai/inference/console
- type: Documentation
  url: https://www.asterlab.ai/inference
- type: GettingStarted
  url: https://www.asterlab.ai/inference
- type: Pricing
  url: https://www.asterlab.ai/inference
- type: SignUp
  url: https://www.asterlab.ai/inference/console
- type: TermsOfService
  url: https://www.asterlab.ai/terms
- type: PrivacyPolicy
  url: https://www.asterlab.ai/privacy
- type: Blog
  url: https://www.asterlab.ai/research/scaling_autonomous_research_to_thousands_of_agents
- type: Support
  url: mailto:info@asterlab.ai
- type: Authentication
  url: authentication/asterlab-authentication.yml
- type: Conventions
  url: conventions/asterlab-conventions.yml
- type: WellKnown
  url: well-known/asterlab-well-known.yml
- type: LLMsTxt
  url: llms/asterlab-llms.txt
- type: DomainSecurity
  url: security/asterlab-domain-security.yml
x-enrichment:
  date: '2026-07-19'
  status: backfilled
  pass: local-v1
  note: backfilled from .gitignore signal + verified work evidence