Moore Threads

Moore Threads (摩尔线程智能科技) is a Chinese GPU company founded in June 2020 that builds full-function GPUs and the MUSA (Meta-computing Unified System Architecture) software stack — a CUDA-alternative programming environment covering the MUSA SDK, muDNN, muBLAS, MCCL, Triton-MUSA and the Musify CUDA-porting toolkit. Alongside the silicon and the SDK it operates a small but real public API surface: the AIBook speech platform (HTTP and WebSocket text-to-speech, streaming and recording-file speech recognition, and streaming voice conversion on aibook-api.mthreads.com), the KUAE Cloud (夸娥云) Coding Plan — an OpenAI- and Anthropic-compatible LLM inference endpoint at coding-plan-endpoint.kuaecloud.net serving GLM-4.7 on MTT S5000 GPUs — and the "摩影元像" digital-human Web SDK distributed on npm as `mtai`. None of these surfaces publishes a machine-readable contract; every operation is documented as prose, parameter tables and curl/Python samples on docs.mthreads.com, and access tokens are issued by contacting sales.

Moore Threads is listed with 4 APIs on the APIs.io network. Tagged areas include Company, GPU, Artificial Intelligence, Machine Learning, and Semiconductors.

The Moore Threads catalog on APIs.io includes 1 event-driven AsyncAPI specification.

Moore Threads’ developer surface includes pricing, documentation, API reference, getting-started guide, support, engineering blog, signup flow, and 20 more developer resources.

🌐 Visit website 📡 Source on GitHub

48.4/100 developing ▬ flat Agent 28/100 agent aware Front door AI 5/6 prominent saas Full breakdown ↓
scored 2026-10-09 · rubric v0.23.0

AccessFreemiumSelf serveFree trial⚡ Free to try

4 APIs

Company GPU Artificial Intelligence Machine Learning Semiconductors Speech Recognition Text-to-Speech Voice Inference Cloud Computing Developer Tools China

Kin Score

Kin Score How this is scored →
scored 2026-10-09 · rubric v0.23.0

Composite quality — 48.4/100 · developing

Contract Quality 8.3 / 21

Developer Ergonomics 9.9 / 17

Access Clarity 10.1 / 17

Operational Transparency 6.4 / 11

Contract Governance 0.0 / 10

Discoverability 6.1 / 9

Regulatory Posture 2.9 / 15

Agent readiness — 28/100 · agent aware

Machine-Readable Contract 18 / 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 6 / 6

Agent Skills 0 / 5

Well-Known Catalog 4 / 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/moore-threads: 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 4

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

Moore Threads AIBook Text-to-Speech API

HTTP and WebSocket speech synthesis. A non-streaming POST /api/v1/tts/generate returns a complete wav/mp3 for up to 300 characters; a WebSocket /api/v2/tts/stream_generate strea...

Moore Threads AIBook Speech Recognition API

Speech-to-text in two shapes. A realtime WebSocket at /api/v1/asr accepts 16 kHz mono audio and returns SentenceBegin / SentenceChanged / SentenceEnd events with optional punctu...

Moore Threads AIBook Streaming Voice Conversion API

A WebSocket voice-conversion service at /api/v1/streaming_vc that re-timbres a live 16 kHz 16-bit mono PCM stream into a target voice and returns 48 kHz PCM. Interaction is Star...

KUAE Cloud Coding Plan API

An LLM inference endpoint operated on Moore Threads MTT S5000 GPUs and sold as a subscription for AI coding tools. It speaks two wire protocols from one host — the Anthropic Mes...

Pricing Plans 1

Published pricing tiers and plan structures.

Moore Threads Plans Pricing

4 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Moore Threads Rate Limits

13 limits

RATE LIMITS

Event Specifications 1

AsyncAPI definitions for this provider's event-driven and streaming APIs.

Moore Threads Webhooks

ASYNCAPI

Security Posture 2

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

Moore Threads Authentication

6 schemes

SECURITY

Moore Threads Domain Security

TLSv1.3 · HSTS

SECURITY

Resources

Get Started 4

Portal, sign-up, and the first successful call

DeveloperPortal

GettingStarted

SignUp

Sandbox

Documentation 2

Reference material describing how the API behaves

Documentation

Documentation

APIReference

APIReference

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

LLMsTxt

LLMsTxt

Design & Contract 6

Pagination, idempotency, versioning, errors, and events

ErrorCatalog

Conventions

Lifecycle

Conformance

Webhooks

Components

Build 3

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

GitHubOrganization

Packages

Packages

SDKs

SDKs

Access & Security 2

Authentication, authorization, and security posture

Authentication

Authentication

DomainSecurity

DomainSecurity

Operate 3

Status, limits, changes, and where to get help

Support

Support

RateLimits

RateLimits

ChangeLog

ChangeLog

Commercial 4

Pricing, plans, and the legal terms of use

Pricing

TermsOfService

PrivacyPolicy

Plans

Company 2

The organization behind the API

Website

Website

Blog

Blog

Source (apis.yml)

aid: moore-threads
name: Moore Threads
description: 'Moore Threads (摩尔线程智能科技) is a Chinese GPU company founded in June 2020 that builds full-function GPUs and the
  MUSA (Meta-computing Unified System Architecture) software stack — a CUDA-alternative programming environment covering the
  MUSA SDK, muDNN, muBLAS, MCCL, Triton-MUSA and the Musify CUDA-porting toolkit. Alongside the silicon and the SDK it operates
  a small but real public API surface: the AIBook speech platform (HTTP and WebSocket text-to-speech, streaming and recording-file
  speech recognition, and streaming voice conversion on aibook-api.mthreads.com), the KUAE Cloud (夸娥云) Coding Plan — an OpenAI-
  and Anthropic-compatible LLM inference endpoint at coding-plan-endpoint.kuaecloud.net serving GLM-4.7 on MTT S5000 GPUs
  — and the "摩影元像" digital-human Web SDK distributed on npm as `mtai`. None of these surfaces publishes a machine-readable
  contract; every operation is documented as prose, parameter tables and curl/Python samples on docs.mthreads.com, and access
  tokens are issued by contacting sales.'
url: https://raw.githubusercontent.com/api-evangelist/moore-threads/refs/heads/main/apis.yml
x-type: company
x-source: harvest:secondary-market
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: freemium
  onboarding: self-serve
  trial: true
  try_now: true
  public: false
  label: Freemium (free trial) · Self-serve signup
  confidence: high
  source:
  - plans
  - authentication
  - rate-limits
  - security
  - sandbox
  generated: '2026-09-02'
  method: derived
specificationVersion: '0.20'
created: '2026-08-26'
modified: '2026-08-26'
image: https://www.mthreads.com/favicon/logo.png
tags:
- Company
- GPU
- Artificial Intelligence
- Machine Learning
- Semiconductors
- Speech Recognition
- Text-to-Speech
- Voice
- Inference
- Cloud Computing
- Developer Tools
- China
tags_raw:
- Company
- GPU
- Artificial Intelligence
- Machine Learning
- Semiconductors
- Speech Recognition
- Text To Speech
- Voice
- LLM Inference
- Cloud Computing
- Developer Tools
- China
- Machine-Learning
apis:
- name: Moore Threads AIBook Text-to-Speech API
  description: HTTP and WebSocket speech synthesis. A non-streaming POST /api/v1/tts/generate returns a complete wav/mp3 for
    up to 300 characters; a WebSocket /api/v2/tts/stream_generate streams base64 PCM chunks with word- and phoneme-level timestamps,
    and additionally accepts streaming TEXT input so an LLM's token stream can be voiced as it is produced. 27 named voices
    are published, split between large-model and lite voices. Authenticated with an Authorization header; tokens are issued
    by contacting Moore Threads.
  humanURL: https://docs.mthreads.com/tts/unary-tts/introduction
  baseURL: https://aibook-api.mthreads.com:32414
  tags:
  - Text-to-Speech
  - Voice
  - Streaming
  tags_raw:
  - Text To Speech
  - Voice
  - Streaming
  properties:
  - type: Documentation
    url: https://docs.mthreads.com/tts/unary-tts/introduction
  - type: APIReference
    url: https://docs.mthreads.com/tts/stream-tts/introduction
- name: Moore Threads AIBook Speech Recognition API
  description: Speech-to-text in two shapes. A realtime WebSocket at /api/v1/asr accepts 16 kHz mono audio and returns SentenceBegin
    / SentenceChanged / SentenceEnd events with optional punctuation, ITN, disfluency removal, speaker diarization, confidence
    and word-level timing. A recording-file HTTP API on the same base submits a job by URL or chunked upload, then polls for
    the transcript or receives it on a callback URL; audio up to 512 MB / 5 hours, results retained 72 hours. Bearer token
    authentication.
  humanURL: https://docs.mthreads.com/asr/recording-recognition/introduction
  baseURL: https://aibook-api.mthreads.com:62220/api/v1/asr
  tags:
  - Speech Recognition
  - Voice
  - Transcription
  properties:
  - type: Documentation
    url: https://docs.mthreads.com/asr/recording-recognition/introduction
  - type: APIReference
    url: https://docs.mthreads.com/asr/realtime-recognition/introduction
- name: Moore Threads AIBook Streaming Voice Conversion API
  description: A WebSocket voice-conversion service at /api/v1/streaming_vc that re-timbres a live 16 kHz 16-bit mono PCM
    stream into a target voice and returns 48 kHz PCM. Interaction is StartConversion → binary audio frames → StopConversion,
    with ConversionStarted / ConversionCompleted / Error control messages. Token passed as a URL query parameter.
  humanURL: https://docs.mthreads.com/vc/stream-vc/introduction
  baseURL: https://aibook-api.mthreads.com:32314
  tags:
  - Voice
  - Streaming
  - Audio
  properties:
  - type: Documentation
    url: https://docs.mthreads.com/vc/stream-vc/introduction
- name: KUAE Cloud Coding Plan API
  description: An LLM inference endpoint operated on Moore Threads MTT S5000 GPUs and sold as a subscription for AI coding
    tools. It speaks two wire protocols from one host — the Anthropic Messages protocol at the root (used by Claude Code)
    and the OpenAI Chat Completions protocol at /v1 (used by Cline, Cursor, Roo Code, Kilo Code and OpenCode) — serving the
    GLM-4.7 model. Authenticated with an API key created in the KUAE Cloud console.
  humanURL: https://docs.mthreads.com/kuaecloud/kuaecloud-doc-online/coding_plan/tools_config
  baseURL: https://coding-plan-endpoint.kuaecloud.net
  tags:
  - Inference
  - Artificial Intelligence
  - Developer Tools
  tags_raw:
  - LLM Inference
  - Artificial Intelligence
  - Developer Tools
  properties:
  - type: Documentation
    url: https://docs.mthreads.com/kuaecloud/kuaecloud-doc-online/coding_plan/tools_config
  - type: GettingStarted
    url: https://docs.mthreads.com/kuaecloud/kuaecloud-doc-online/coding_plan/user_guide
  - type: SignUp
    url: https://coding-plan.kuaecloud.net/free_apply
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Pricing
  url: https://docs.mthreads.com/kuaecloud/kuaecloud-doc-online/coding_plan/plan_overview
- type: Website
  url: https://www.mthreads.com/
- type: DeveloperPortal
  url: https://developer.mthreads.com
- type: Documentation
  url: https://docs.mthreads.com/
- type: APIReference
  url: https://docs.mthreads.com/tts/stream-tts/introduction
- type: GettingStarted
  url: https://docs.mthreads.com/kuaecloud/kuaecloud-doc-online/coding_plan/user_guide
- type: Support
  url: https://www.mthreads.com/support/FAQ
- type: Blog
  url: https://blog.mthreads.com
- type: GitHubOrganization
  url: https://github.com/MooreThreads
- type: SignUp
  url: https://coding-plan.kuaecloud.net/free_apply
- type: TermsOfService
  url: https://docs.mthreads.com/kuaecloud/kuaecloud-doc-online/terms/user_agreement
- type: PrivacyPolicy
  url: https://www.mthreads.com/privacy
- type: Authentication
  url: authentication/moore-threads-authentication.yml
- type: ErrorCatalog
  url: errors/moore-threads-error-codes.yml
- type: Conventions
  url: conventions/moore-threads-conventions.yml
- type: RateLimits
  url: rate-limits/moore-threads-rate-limits.yml
- type: Plans
  url: plans/moore-threads-plans-pricing.yml
- type: Packages
  url: packages/moore-threads-packages.yml
- type: SDKs
  url: packages/moore-threads-packages.yml
- type: LLMsTxt
  url: llms/moore-threads-llms.txt
- type: Lifecycle
  url: lifecycle/moore-threads-lifecycle.yml
- type: ChangeLog
  url: changelog/moore-threads-changelog.yml
- type: Conformance
  url: conformance/moore-threads-conformance.yml
- type: DomainSecurity
  url: security/moore-threads-domain-security.yml
- type: Webhooks
  url: asyncapi/moore-threads-webhooks.yml
- type: Sandbox
  url: sandbox/moore-threads-sandbox.yml
- type: Components
  url: components/moore-threads-components.yml
x-enrichment:
  date: '2026-08-26'
  status: enriched
  artifacts_added: 16
  pass: local-v1
x-coverage:
  state: covered
  reason: null
  detail: Moore Threads has a real, fully documented public API surface — AIBook TTS/ASR/voice conversion on aibook-api.mthreads.com
    and the KUAE Cloud Coding Plan LLM endpoint — but publishes no machine-readable contract for any of it; every artifact
    here was read from the prose API references on docs.mthreads.com.
  evidence:
  - url: https://docs.mthreads.com/tts/unary-tts/introduction
    status: 200
  - url: https://docs.mthreads.com/kuaecloud/kuaecloud-doc-online/coding_plan/tools_config
    status: 200
  - url: https://aibook-api.mthreads.com:62220/openapi.json
    status: 404
  checked: '2026-08-26'

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/moore-threads"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/moore-threads/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/moore-threads/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.