KaiGPT

KaiGPT (gptzzz.ai, site name "gptzzz.ai", subtitle "AI API 中转服务 中转站") is an independent third-party AI API relay (中转站) and multi-model gateway for Chinese-speaking developers. It exposes an OpenAI-compatible interface at https://gptzzz.ai/v1 (chat completions, Responses, embeddings, images), a Claude Messages route at https://gptzzz.ai/v1/messages and a Gemini-style v1beta surface, authenticated with a KaiGPT API key via Authorization Bearer, x-api-key or x-goog-api-key. Model IDs, group multipliers and limits are shown only in the logged-in console; the public model plaza lists no models or prices yet. It also ships a desktop client that configures Claude Code, Codex, Gemini CLI and OpenCode, and a Chinese knowledge base on relay selection, security and compliance. KaiGPT states it is not affiliated with the model vendors it routes to; it resells access to other providers' model APIs rather than training models itself.

KaiGPT is listed with 2 APIs on the APIs.io network. Tagged areas include Artificial Intelligence, LLM Gateway, API Relay, OpenAI-Compatible, and Claude.

KaiGPT’s developer surface includes authentication, documentation, getting-started guide, support, engineering blog, signup flow, and 14 more developer resources.

🌐 Visit website 📡 Source on GitHub
17.8/100 emerging ▬ flat Agent 8/100 agent aware Front door AI 5/6 prominent Full breakdown ↓
scored 2026-10-09 · rubric v0.23.0
2 APIs
Artificial IntelligenceLLM GatewayAPI RelayOpenAI-CompatibleClaudeGeminiLLMChina

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-10-09 · rubric v0.23.0
Composite quality — 17.8/100 · emerging
Contract Quality 0.0 / 21
Developer Ergonomics 6.9 / 17
Access Clarity 2.2 / 17
Operational Transparency 1.7 / 11
Contract Governance 0.0 / 10
Discoverability 4.9 / 9
Regulatory Posture 1.6 / 15
Agent readiness — 8/100 · 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 0 / 3
A2A Agent Card 0 / 8
Dry-Run / Simulate Mode 0 / 4
Delegated User Identity 0 / 6
Protected Resource Metadata 0 / 5
Registration Without a Human 0 / 6
Agentic Commerce Well-Known Document 0 / 5
Regulatory Posture applies to this provider. Its tags matched the Horizontal (data, software, accessibility, platform) regime, so Regulatory Posture carries 15 points of the composite. If this regime is wrong for your business, say so on your provider repo — the applicability map is public and we will correct it.
Create-or-Update Ergonomics could not be measured. We hold no machine-readable contract for this provider to read, so there is nothing to measure a write surface against. Excluded rather than scored zero: never-measured and measured-empty are different facts. Publishing an OpenAPI is what makes this facet — and several others — scorable at all.
The six quality facets above are damped to 85 points between them, because the conditional facet above carries the other 15. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 85% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from github.com/api-evangelist/gptzzz: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

APIs 2

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

KaiGPT OpenAI-Compatible API

OpenAI-compatible relay interface. The docs give the Base URL https://gptzzz.ai/v1 for OpenAI-compatible clients (which append /chat/completions or /responses); requests are aut...

KaiGPT Claude Messages API

Claude Messages relay route. The docs give https://gptzzz.ai/v1/messages for Claude Messages requests and say Claude clients must use that protocol configuration rather than the...

Pricing Plans 1

Published pricing tiers and plan structures.

Gptzzz Plans Pricing

0 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Gptzzz Rate Limits

0 limits

RATE LIMITS

Security Posture 2

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

Gptzzz Authentication

3 schemes

SECURITY

Gptzzz Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Resources

Get Started 3

Portal, sign-up, and the first successful call

GettingStarted
GettingStarted
 SignUp
SignUp
 Login
Login

Documentation 2

Reference material describing how the API behaves

Documentation
Documentation
 Documentation
Documentation

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

LLMsTxt
LLMsTxt

Design & Contract 4

Pagination, idempotency, versioning, errors, and events

Conventions
Conventions
 Lifecycle
Lifecycle
 ErrorCatalog
ErrorCatalog
 ErrorCodes
ErrorCodes

Access & Security 2

Authentication, authorization, and security posture

Authentication
Authentication
 DomainSecurity
DomainSecurity

Operate 3

Status, limits, changes, and where to get help

RateLimits
RateLimits
 StatusPage
StatusPage
 Support
Support

Commercial 1

Pricing, plans, and the legal terms of use

Plans
Plans

Company 2

The organization behind the API

Website
Website
 Blog
Blog

Other 2

Properties that don't map to a standard resource type

Hosts
Hosts
 Vendors
Vendors

Source (apis.yml)

apis.yml Raw ↑ 
name: KaiGPT
image: https://gptzzz.ai/blog/assets/og-cover.png
aid: gptzzz
description: KaiGPT (gptzzz.ai, site name "gptzzz.ai", subtitle "AI API 中转服务 中转站") is an independent third-party AI API relay
  (中转站) and multi-model gateway for Chinese-speaking developers. It exposes an OpenAI-compatible interface at https://gptzzz.ai/v1
  (chat completions, Responses, embeddings, images), a Claude Messages route at https://gptzzz.ai/v1/messages and a Gemini-style
  v1beta surface, authenticated with a KaiGPT API key via Authorization Bearer, x-api-key or x-goog-api-key. Model IDs, group
  multipliers and limits are shown only in the logged-in console; the public model plaza lists no models or prices yet. It
  also ships a desktop client that configures Claude Code, Codex, Gemini CLI and OpenCode, and a Chinese knowledge base on
  relay selection, security and compliance. KaiGPT states it is not affiliated with the model vendors it routes to; it resells
  access to other providers' model APIs rather than training models itself.
url: https://raw.githubusercontent.com/api-evangelist/gptzzz/refs/heads/main/apis.yml
x-type: company
x-source: apis-io-submission
x-submitted-by: lin009hg@gmail.com, apis.io/add 2026-09-22
x-tier: profiled
x-tier-reason: enrichment pass 2026-09-23 (local-v5; was apis.io/add submission worked by the support sweep 2026-09-23; host
  probed healthy (root 200, invented path 404, llms.txt 200); listed on Kin's decision 2026-09-23 despite relay/reseller posture)
specificationVersion: '0.23'
created: '2026-09-23'
modified: '2026-09-23'
tags:
- Artificial Intelligence
- LLM Gateway
- API Relay
- OpenAI-Compatible
- Claude
- Gemini
- LLM
- China
tags_raw:
- Artificial Intelligence
- LLM Gateway
- API Relay
- OpenAI Compatible
- Claude
- Gemini
- Large Language Models
- China
common:
- type: Plans
  url: plans/gptzzz-plans-pricing.yml
- type: RateLimits
  url: rate-limits/gptzzz-rate-limits.yml
- type: Conventions
  url: conventions/gptzzz-conventions.yml
- type: Authentication
  url: authentication/gptzzz-authentication.yml
- type: Lifecycle
  url: lifecycle/gptzzz-lifecycle.yml
- type: ErrorCatalog
  url: errors/gptzzz-problem-types.yml
- type: LLMsTxt
  url: llms/gptzzz-llms.txt
- type: Hosts
  url: hosts/gptzzz-hosts.yml
- type: Vendors
  url: vendors/gptzzz-vendors.yml
- type: StatusPage
  url: https://gptzzz.ai/status/
- type: DomainSecurity
  url: security/gptzzz-domain-security.yml
- type: Website
  url: https://gptzzz.ai/
- type: Documentation
  url: https://gptzzz.ai/docs/
- type: GettingStarted
  url: https://gptzzz.ai/blog/api-zhongzhuan-how-to-use/
- type: Support
  url: https://gptzzz.ai/support/
- type: Blog
  url: https://gptzzz.ai/blog/
- type: SignUp
  url: https://gptzzz.ai/register
- type: Login
  url: https://gptzzz.ai/login
- type: Documentation
  url: https://gptzzz.ai/docs/glossary/
- type: ErrorCodes
  url: https://gptzzz.ai/docs/api-error-codes/
maintainers:
- FN: KaiGPT Support
  email: support@gptzzz.ai
apis:
- aid: gptzzz:kaigpt-openai-compatible-api
  name: KaiGPT OpenAI-Compatible API
  description: 'OpenAI-compatible relay interface. The docs give the Base URL https://gptzzz.ai/v1 for OpenAI-compatible clients
    (which append /chat/completions or /responses); requests are authenticated with a KaiGPT API key sent as Authorization:
    Bearer. Available model IDs, multipliers and limits are shown in the logged-in console.'
  humanURL: https://gptzzz.ai/docs/
  baseURL: https://gptzzz.ai/v1
  tags:
  - OpenAI-Compatible
  - Chat
  - LLM Gateway
  tags_raw:
  - OpenAI Compatible
  - Chat
  - LLM Gateway
  properties:
  - type: Documentation
    url: https://gptzzz.ai/docs/
  - type: Documentation
    url: https://gptzzz.ai/blog/openai-api-quickstart/
  - type: Documentation
    url: https://gptzzz.ai/blog/openai-compatible-api-migration/
- aid: gptzzz:kaigpt-claude-messages-api
  name: KaiGPT Claude Messages API
  description: Claude Messages relay route. The docs give https://gptzzz.ai/v1/messages for Claude Messages requests and say
    Claude clients must use that protocol configuration rather than the OpenAI request body; the gateway accepts the key in
    the x-api-key header.
  humanURL: https://gptzzz.ai/blog/claude-api-quickstart/
  tags:
  - Claude
  - Message
  - LLM Gateway
  tags_raw:
  - Claude
  - Messages
  - LLM Gateway
  properties:
  - type: Documentation
    url: https://gptzzz.ai/docs/
  - type: Documentation
    url: https://gptzzz.ai/blog/claude-api-quickstart/
  - type: Documentation
    url: https://gptzzz.ai/blog/claude-code-api-relay/
x-enrichment:
  date: '2026-09-23'
  status: enriched
  artifacts_added: 13
  pass: local-v5

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

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

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

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