WeaveAPI - OpenAI-compatible AI API Gateway

deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: false
  label: Hosted service · you call their endpoint
  confidence: medium
  source:
  - pricing
  generated: '2026-08-28'
  method: derived
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
- 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
- AI Inference
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
  - 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
  - AI Inference
  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
  - Inference
  - Anthropic Compatible
  - Agent Tools
  - Model Routing
  tags_raw:
  - AI
  - LLM
  - AI inference
  - Anthropic-compatible
  - agent tools
  - model routing
  - AI Inference
  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.'