Martian website screenshot

Martian

Martian operates the Martian Gateway, a unified LLM API that provides access to 200+ AI models from leading providers (OpenAI, Anthropic, and others) through a single OpenAI- and Anthropic-compatible endpoint. Developers point the standard OpenAI or Anthropic SDK at https://api.withmartian.com/v1, authenticate with a bearer API key, and call models using a provider/model-name identifier, with real-time pricing, a usage dashboard, and model routing across providers. Martian is also an AI interpretability research organization, publishing open-source frameworks such as ARES (Agentic Research and Evaluation Suite), K-Steering, RouterBench, and a model-router / judges SDK.

Martian publishes 1 API on the APIs.io network. Tagged areas include Company, Artificial Intelligence, LLM, LLM Gateway, and Model Router.

Martian’s developer surface includes documentation, API reference, getting-started guide, support, engineering blog, signup flow, authentication, and 15 more developer resources.

28.1/100 emerging ▬ flat Agent 33/100 agent aware Full breakdown ↓
scored 2026-07-27 · rubric v0.5
AccessSelf serve
1 APIs 1 MCP Servers
CompanyArtificial IntelligenceLLMLLM GatewayModel RouterMachine LearningInterpretabilityInferenceOpenAI CompatibleDeveloper Tools

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 28.1/100 · emerging
Contract Quality 0.0 / 25
Developer Ergonomics 13.5 / 20
Commercial Clarity 2.6 / 20
Operational Transparency 2.7 / 13
Governance 0.0 / 12
Discoverability 9.3 / 10
Agent readiness — 33/100 · agent aware
Machine-Readable Contract 0 / 18
Agentic Access Contract 0 / 15
MCP Server 12 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 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/martian: 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.

Martian Gateway API

Unified, OpenAI- and Anthropic-compatible LLM gateway providing access to 200+ models from leading providers through a single endpoint. Documented operations: POST /v1/chat/comp...

MCP Servers 1

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

martian-mcp.yml

MCP SERVER

Security Posture 2

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

Martian Authentication

apiKey · 1 scheme

SECURITY

Martian Domain Security

TLSv1.3 · HSTS · DNSSEC · DMARC

SECURITY

Resources

Get Started 4

Portal, sign-up, and the first successful call

Documentation 2

Reference material describing how the API behaves

Agent Surfaces 3

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 4

Pagination, idempotency, versioning, errors, and events

Build 3

SDKs, sample code, and the tooling you integrate with

Access & Security 2

Authentication, authorization, and security posture

Operate 2

Status, limits, changes, and where to get help

Company 2

The organization behind the API

Source (apis.yml)

apis.yml Raw ↑
aid: martian
name: Martian
description: Martian operates the Martian Gateway, a unified LLM API that provides access to 200+ AI models from leading providers
  (OpenAI, Anthropic, and others) through a single OpenAI- and Anthropic-compatible endpoint. Developers point the standard
  OpenAI or Anthropic SDK at https://api.withmartian.com/v1, authenticate with a bearer API key, and call models using a provider/model-name
  identifier, with real-time pricing, a usage dashboard, and model routing across providers. Martian is also an AI interpretability
  research organization, publishing open-source frameworks such as ARES (Agentic Research and Evaluation Suite), K-Steering,
  RouterBench, and a model-router / judges SDK.
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://withmartian.com/favicon.ico
url: https://raw.githubusercontent.com/api-evangelist/martian/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- general-catalyst
x-tier: stub
x-tier-reason: portfolio-lead
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-20'
tags:
- Company
- Artificial Intelligence
- LLM
- LLM Gateway
- Model Router
- Machine Learning
- Interpretability
- Inference
- OpenAI Compatible
- Developer Tools
apis:
- name: Martian Gateway API
  description: 'Unified, OpenAI- and Anthropic-compatible LLM gateway providing access to 200+ models from leading providers
    through a single endpoint. Documented operations: POST /v1/chat/completions (OpenAI-compatible), POST /v1/messages (Anthropic-compatible),
    and GET /v1/models (List Models). Bearer API key authentication; models are addressed as provider/model-name.'
  humanURL: https://docs.withmartian.com/gateway
  baseURL: https://api.withmartian.com/v1
  tags:
  - LLM
  - LLM Gateway
  - AI
  - Inference
  - OpenAI Compatible
  - Anthropic Compatible
  properties:
  - type: Documentation
    url: https://docs.withmartian.com
  - type: APIReference
    url: https://docs.withmartian.com/api-reference
  - type: GettingStarted
    url: https://docs.withmartian.com/quickstart
  - type: Authentication
    url: authentication/martian-authentication.yml
  - type: Conventions
    url: conventions/martian-conventions.yml
  - type: ErrorCatalog
    url: errors/martian-error-codes.yml
  - type: Conformance
    url: conformance/martian-conformance.yml
common:
- type: DomainSecurity
  url: security/martian-domain-security.yml
- type: Website
  url: https://withmartian.com
- type: DeveloperPortal
  url: https://docs.withmartian.com
- type: Documentation
  url: https://docs.withmartian.com
- type: APIReference
  url: https://docs.withmartian.com/api-reference
- type: GettingStarted
  url: https://docs.withmartian.com/quickstart
- type: Support
  url: https://docs.withmartian.com/resources/support
- type: Blog
  url: https://withmartian.com/blog
- type: GitHubOrganization
  url: https://github.com/withmartian
- type: SignUp
  url: https://app.withmartian.com/
- type: Login
  url: https://app.withmartian.com/
- type: StatusPage
  url: https://status.withmartian.com
- type: Packages
  url: packages/martian-packages.yml
- type: SDKs
  url: packages/martian-packages.yml
- type: Authentication
  url: authentication/martian-authentication.yml
- type: Conventions
  url: conventions/martian-conventions.yml
- type: ErrorCatalog
  url: errors/martian-error-codes.yml
- type: Lifecycle
  url: lifecycle/martian-lifecycle.yml
- type: Conformance
  url: conformance/martian-conformance.yml
- type: WellKnown
  url: well-known/martian-well-known.yml
- type: MCPServer
  url: mcp/martian-mcp.yml
- type: LLMsTxt
  url: llms/martian-llms.txt
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
x-enrichment:
  date: '2026-07-20'
  status: enriched
  artifacts_added: 10
  pass: local-v1