WeaveAPI - OpenAI-compatible AI API Gateway

WeaveAPI is a hosted, OpenAI-wire-compatible inference gateway: one base URL (https://api.weaveapi.dev/v1) and one bearer API key give access to model routes drawn from several upstream families, while keys, prepaid balance, usage logs and top-ups are managed in a hosted console. The pitch is drop-in substitution — keep an existing OpenAI SDK, change the base URL and the key, and pick a model id from the console Model Marketplace. It also exposes an Anthropic-compatible messages route, and publishes setup guides for Claude Code, Codex, OpenCode, OpenClaw, Claude Desktop and Hermes via CC Switch. Billing is prepaid credits shared across every route, metered per model, with a $1 signup testing credit and no subscription tiers. The gateway runs the open-source New API platform. WeaveAPI publishes no OpenAPI or other machine-readable contract, no SDK of its own, no MCP server, no status page and no changelog.

WeaveAPI - OpenAI-compatible AI API Gateway publishes 2 APIs on the APIs.io network. Tagged areas include Artificial Intelligence, LLM, AI Inference, API Gateway, and Aggregator.

WeaveAPI - OpenAI-compatible AI API Gateway’s developer surface includes documentation, API reference, getting-started guide, support, pricing, signup flow, authentication, and 16 more developer resources.

33.9/100 thin ▬ flat Agent 18/100 agent aware Full breakdown ↓
scored 2026-08-21 · rubric v0.12.0
AccessPaidSelf serveFree trial
2 APIs
Artificial IntelligenceLLMAI InferenceAPI GatewayAggregatorOpenAI-CompatibleDeveloper ToolsModel RoutingLLM Gatewayprepaid creditsAgent ToolsModel Marketplace

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-08-21 · rubric v0.12.0
Composite quality — 33.9/100 · thin
Contract Quality 0.0 / 25
Developer Ergonomics 11.0 / 20
Access Clarity 13.2 / 20
Operational Transparency 0.0 / 13
Contract Governance 2.2 / 12
Discoverability 7.6 / 10
Agent readiness — 18/100 · agent aware
Machine-Readable Contract 0 / 18
Agentic Access Contract 0 / 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 3 / 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/weaveapi: 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 2

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

WeaveAPI OpenAI-compatible API

OpenAI-wire-compatible REST API for chat completions, responses-style requests and the model catalog, authenticated with a bearer API key in the Authorization header. Three endp...

WeaveAPI Anthropic-compatible Messages API

Anthropic/Claude-wire-compatible messages route served from the bare api.weaveapi.dev host. The Claude Code setup guide instructs clients to use the host WITHOUT /v1 because Cla...

Pricing Plans 1

Published pricing tiers and plan structures.

Rate Limits 1

Documented rate limits and quota policies.

Weaveapi Rate Limits

0 limits

RATE LIMITS

Security Posture 2

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

Weaveapi Authentication

apiKey · 0 schemes

SECURITY

Weaveapi Domain Security

TLSv1.3 · HSTS · 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 1

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 4

Pagination, idempotency, versioning, errors, and events

Build 1

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

Commercial 4

Pricing, plans, and the legal terms of use

Company 2

The organization behind the API

Other 1

Properties that don't map to a standard resource type

Source (apis.yml)

apis.yml Raw ↑
accessModel:
  pricing: paid
  onboarding: self-serve
  trial: true
  try_now: false
  public: false
  label: Paid · Self-serve signup
  confidence: high
  source:
  - https://weaveapi.dev/pricing/
  - https://console.weaveapi.dev/register
  - plans
  - authentication
  generated: '2026-08-11'
  method: searched
  note: Standing model is prepaid pay-as-you-go credits — you must fund a balance before calling anything — so pricing is
    `paid`, with trial true for the $1 signup testing credit. Signup is self-serve at the console (password, GitHub or Google),
    but no endpoint is callable without a key, so public is false.
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/weaveapi.png
name: WeaveAPI - OpenAI-compatible AI API Gateway
description: 'WeaveAPI is a hosted, OpenAI-wire-compatible inference gateway: one base URL (https://api.weaveapi.dev/v1) and
  one bearer API key give access to model routes drawn from several upstream families, while keys, prepaid balance, usage
  logs and top-ups are managed in a hosted console. The pitch is drop-in substitution — keep an existing OpenAI SDK, change
  the base URL and the key, and pick a model id from the console Model Marketplace. It also exposes an Anthropic-compatible
  messages route, and publishes setup guides for Claude Code, Codex, OpenCode, OpenClaw, Claude Desktop and Hermes via CC
  Switch. Billing is prepaid credits shared across every route, metered per model, with a $1 signup testing credit and no
  subscription tiers. The gateway runs the open-source New API platform. WeaveAPI publishes no OpenAPI or other machine-readable
  contract, no SDK of its own, no MCP server, no status page and no changelog.'
url: https://raw.githubusercontent.com/api-evangelist/weaveapi/refs/heads/main/apis.yml
created: '2026-07-10'
modified: '2026-08-11'
specificationVersion: '0.23'
tags:
- Artificial Intelligence
- LLM
- AI Inference
- API Gateway
- Aggregator
- OpenAI-Compatible
- Developer Tools
- Model Routing
- LLM Gateway
- prepaid credits
- Agent Tools
- Model Marketplace
tags_raw:
- AI
- LLM
- AI inference
- API gateway
- aggregator
- OpenAI-compatible
- developer tools
- model routing
- LLM gateway
- prepaid credits
- agent tools
- model marketplace
apis:
- name: WeaveAPI OpenAI-compatible API
  description: OpenAI-wire-compatible REST API for chat completions, responses-style requests and the model catalog, authenticated
    with a bearer API key in the Authorization header. Three endpoints are documented (POST /v1/chat/completions, POST /v1/responses,
    GET /v1/models); probing shows a further dozen OpenAI-style routes registered on the gateway but undocumented. No OpenAPI
    is published, so request and response schemas are inherited from the OpenAI wire format rather than specified by WeaveAPI.
  humanURL: https://weaveapi.dev/docs/
  baseURL: https://api.weaveapi.dev/v1
  tags:
  - Artificial Intelligence
  - LLM
  - AI Inference
  - API Gateway
  - Aggregator
  - OpenAI-Compatible
  - Developer Tools
  - Model Routing
  tags_raw:
  - AI
  - LLM
  - AI inference
  - API gateway
  - aggregator
  - OpenAI-compatible
  - developer tools
  - model routing
  properties:
  - type: Documentation
    url: https://weaveapi.dev/docs/
  - type: APIReference
    url: https://weaveapi.dev/docs/#chat-completions
  - type: GettingStarted
    url: https://weaveapi.dev/docs/#quick-start
  - type: Authentication
    url: https://weaveapi.dev/docs/#api-keys
  - type: Conventions
    url: conventions/weaveapi-conventions.yml
  - type: ErrorCatalog
    url: errors/weaveapi-error-codes.yml
  - type: RateLimits
    url: rate-limits/weaveapi-rate-limits.yml
- name: WeaveAPI Anthropic-compatible Messages API
  description: Anthropic/Claude-wire-compatible messages route served from the bare api.weaveapi.dev host. The Claude Code
    setup guide instructs clients to use the host WITHOUT /v1 because Claude-compatible clients build the messages path themselves;
    the route resolves at POST /v1/messages and is confirmed live and auth-gated. Uses the same WeaveAPI bearer key. No model
    in the public catalog declares Anthropic endpoint support, so which routes answer here is not publicly verifiable.
  humanURL: https://weaveapi.dev/docs/claude-code-cc-switch/
  baseURL: https://api.weaveapi.dev
  tags:
  - Artificial Intelligence
  - LLM
  - AI Inference
  - Anthropic Compatible
  - Agent Tools
  - Model Routing
  tags_raw:
  - AI
  - LLM
  - AI inference
  - Anthropic-compatible
  - agent tools
  - model routing
  properties:
  - type: Documentation
    url: https://weaveapi.dev/docs/claude-code-cc-switch/
  - type: Authentication
    url: authentication/weaveapi-authentication.yml
maintainers:
- FN: WeaveAPI - OpenAI-compatible AI API Gateway
  url: https://weaveapi.dev/
  email: support@weaveapi.dev
common:
- type: Website
  url: https://weaveapi.dev/
- type: DeveloperPortal
  url: https://console.weaveapi.dev/
- type: Documentation
  url: https://weaveapi.dev/docs/
- type: APIReference
  url: https://weaveapi.dev/docs/#chat-completions
- type: GettingStarted
  url: https://weaveapi.dev/docs/#quick-start
- type: Support
  url: https://weaveapi.dev/support/
- type: Pricing
  url: https://weaveapi.dev/pricing/
- type: SignUp
  url: https://console.weaveapi.dev/register
- type: Login
  url: https://console.weaveapi.dev/login
- type: TermsOfService
  url: https://weaveapi.dev/terms/
- type: PrivacyPolicy
  url: https://weaveapi.dev/privacy/
- type: About
  url: https://weaveapi.dev/about/
- type: Authentication
  url: authentication/weaveapi-authentication.yml
- type: Conventions
  url: conventions/weaveapi-conventions.yml
- type: ErrorCatalog
  url: errors/weaveapi-error-codes.yml
- type: RateLimits
  url: rate-limits/weaveapi-rate-limits.yml
- type: Plans
  url: plans/weaveapi-plans-pricing.yml
- type: Lifecycle
  url: lifecycle/weaveapi-lifecycle.yml
- type: Conformance
  url: conformance/weaveapi-conformance.yml
- type: Packages
  url: packages/weaveapi-packages.yml
- type: LLMsTxt
  url: llms/weaveapi-llms.txt
- type: ContentSignal
  url: well-known/weaveapi-content-signals.yml
- type: DomainSecurity
  url: security/weaveapi-domain-security.yml
generated:
  by: apis.io/add
  model: claude-opus-4-8
  confidence: 85
  at: '2026-07-10T05:46:24.844Z'
x-enrichment:
  date: '2026-08-11'
  status: enriched
  artifacts_added: 15
  pass: local-v1
x-base-url-check:
  date: '2026-08-11'
  verdict_from_tool: no-usable-base
  accepted: false
  reason: 'repair-api-bases.py flagged api.weaveapi.dev as `nonprod-host`, which is a false positive on the .dev TLD — weaveapi.dev
    is the company''s production domain, not a development environment. The base URL was verified live on 2026-08-11: GET
    https://api.weaveapi.dev/v1/models returns 401 with the gateway''s auth challenge, and the docs, about page, pricing page
    and all six agent setup guides name https://api.weaveapi.dev/v1 as the base. Left unchanged.'

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

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

Get an API key

Free tier, no email required.

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