FuriosaAI website screenshot

FuriosaAI

FuriosaAI is a South Korean semiconductor company that designs data-center AI inference chips and the software stack that runs on them. Its second-generation NPU, RNGD, implements a Tensor Contraction Processor architecture on TSMC 5nm and targets LLM, multi-modal and vision inference. The developer surface is software you run yourself rather than a hosted API: Furiosa-LLM ships an OpenAI-compatible server exposing chat, completions, responses, embeddings, score, rerank, models, tokenizer and Prometheus metrics endpoints, and the earlier Furiosa Model Server implements the KServe v2 Predict Protocol and the Triton Model Repository extension over REST and gRPC. Around that sit Python, Go and Rust packages, a furiosa-smi device CLI, container images, an APT/RPM package repository, and a Kubernetes cloud-native toolkit (device plugin, DRA driver, feature discovery, metrics exporter, NPU operator).

FuriosaAI publishes 4 APIs on the APIs.io network, including Health API, Models API, Predict API, and 1 more. Tagged areas include Artificial Intelligence, Machine-Learning, Inference, Semiconductors, and NPU.

FuriosaAI’s developer surface includes documentation, API reference, getting-started guide, support, engineering blog, changelog, signup flow, and 27 more developer resources.

🌐 Visit website 📡 Source on GitHub
43.8/100 developing ▬ flat Agent 22/100 agent aware Full breakdown ↓
scored 2026-09-08 · rubric v0.20.0
AccessApproval
2 APIs
Artificial IntelligenceMachine-LearningInferenceSemiconductorsNPUHardwareLLMModel ServingKubernetesDeveloper ToolsComputeInfrastructure

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-09-08 · rubric v0.20.0
Composite quality — 43.8/100 · developing
Contract Quality 8.8 / 23
Developer Ergonomics 14.5 / 18
Access Clarity 4.3 / 18
Operational Transparency 3.7 / 12
Contract Governance 2.0 / 11
Discoverability 6.8 / 9
Create-or-Update Ergonomics 0.0 / 10
Agent readiness — 22/100 · 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 0 / 6
Agent Skills 5 / 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
Create-or-Update Ergonomics applies to this provider. This API accepts writes, so it carries 10 points of the composite. It is scored from the published contracts themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in front of it, and the first time that check is skipped a duplicate record is created. Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet, not penalised by it.
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/furiosa: 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 5

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

Furiosa-LLM OpenAI-Compatible Server

The HTTP server started by `furiosa-llm serve `. It hosts a single model on RNGD NPUs and exposes an OpenAI-compatible surface - /v1/completions, /v1/chat/complet...

FuriosaAI Health API

The Health API from FuriosaAI — 2 operation(s) for health.

FuriosaAI Models API

The Models API from FuriosaAI — 3 operation(s) for models.

FuriosaAI Predict API

The Predict API API from FuriosaAI — 1 operation(s) for predict api.

FuriosaAI Repository API

The Repository API from FuriosaAI — 3 operation(s) for repository.

Pricing Plans 1

Published pricing tiers and plan structures.

Furiosa Plans Pricing

0 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Furiosa Rate Limits

0 limits

RATE LIMITS

Security Posture 2

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

Furiosa Authentication

0 schemes

SECURITY

Furiosa Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Resources

Get Started 4

Portal, sign-up, and the first successful call

DeveloperPortal
DeveloperPortal
 GettingStarted
GettingStarted
 SignUp
SignUp
 Sandbox
Sandbox

Documentation 2

Reference material describing how the API behaves

Documentation
Documentation
 APIReference
APIReference

Agent Surfaces 2

MCP servers, agent skills, and machine-readable catalogs

LLMsTxt
LLMsTxt
 AgentSkill
AgentSkill

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Conventions
Conventions
 ErrorCatalog
ErrorCatalog
 Lifecycle
Lifecycle
 Conformance
Conformance
 DataModel
DataModel

Build 4

SDKs, sample code, and the tooling you integrate with

GitHubOrganization
GitHubOrganization
 Packages
Packages
 SDKs
SDKs
 CLI
CLI

Access & Security 2

Authentication, authorization, and security posture

Authentication
Authentication
 DomainSecurity
DomainSecurity

Operate 8

Status, limits, changes, and where to get help

Support
Support
 Community
Community
 Roadmap
Roadmap
 ChangeLog
ChangeLog
 Contact
Contact
 Deprecation
Deprecation
 RateLimits
RateLimits
 ChangeLog
ChangeLog

Scroll for all 8

Commercial 3

Pricing, plans, and the legal terms of use

License
License
 PrivacyPolicy
PrivacyPolicy
 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

Overlay
Overlay
 Overlay
Overlay

Source (apis.yml)

apis.yml Raw ↑ 
aid: furiosa
name: FuriosaAI
description: 'FuriosaAI is a South Korean semiconductor company that designs data-center AI inference chips and the software
  stack that runs on them. Its second-generation NPU, RNGD, implements a Tensor Contraction Processor architecture on TSMC
  5nm and targets LLM, multi-modal and vision inference. The developer surface is software you run yourself rather than a
  hosted API: Furiosa-LLM ships an OpenAI-compatible server exposing chat, completions, responses, embeddings, score, rerank,
  models, tokenizer and Prometheus metrics endpoints, and the earlier Furiosa Model Server implements the KServe v2 Predict
  Protocol and the Triton Model Repository extension over REST and gRPC. Around that sit Python, Go and Rust packages, a furiosa-smi
  device CLI, container images, an APT/RPM package repository, and a Kubernetes cloud-native toolkit (device plugin, DRA driver,
  feature discovery, metrics exporter, NPU operator).'
url: https://raw.githubusercontent.com/api-evangelist/furiosa/refs/heads/main/apis.yml
x-type: company
x-source: harvest:secondary-market
deliveryModel:
  model: unknown
  open_source: unknown
  commercial: true
  callable_host: false
  label: Delivery model not determined — needs a product licence on record
  confidence: low
  source:
  - openapi
  - pricing
  - repository-unlicensed
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: unknown
  onboarding: approval
  trial: false
  try_now: false
  public: false
  label: Requires approval
  confidence: medium
  source:
  - plans
  - authentication
  - rate-limits
  - security
  - sandbox
  generated: '2026-09-03'
  method: derived
specificationVersion: '0.23'
created: '2026-08-16'
modified: '2026-08-16'
image: https://furiosa.ai/favicon.ico
tags:
- Artificial Intelligence
- Machine-Learning
- Inference
- Semiconductors
- NPU
- Hardware
- LLM
- Model Serving
- Kubernetes
- Developer Tools
- Compute
- Infrastructure
tags_raw:
- Artificial Intelligence
- Machine Learning
- Inference
- Semiconductors
- NPU
- Hardware
- LLM
- Model Serving
- Kubernetes
- Developer Tools
- Compute
- Infrastructure
apis:
- aid: furiosa-llm-openai-server
  name: Furiosa-LLM OpenAI-Compatible Server
  description: The HTTP server started by `furiosa-llm serve <ARTIFACT_PATH>`. It hosts a single model on RNGD NPUs and exposes
    an OpenAI-compatible surface - /v1/completions, /v1/chat/completions, /v1/responses (OpenResponses), /v1/embeddings, /v1/models,
    /v1/models/{model_id} - plus the vLLM-originated /score and /rerank pooling endpoints, a tokenizer API (/tokenize, /detokenize,
    /tokenizer_info), GET /version and a Prometheus GET /metrics endpoint. It is customer-hosted software, so the base URL
    below is templated on the operator's own host; the documented default is http://localhost:8000/v1. FuriosaAI publishes
    no OpenAPI for this surface - the parameter tables in the serving docs are the contract.
  humanURL: https://developer.furiosa.ai/latest/en/furiosa_llm/furiosa-llm-serve.html
  baseURL: http://{furiosa_llm_host}:8000/v1
  tags:
  - LLM
  - Inference
  - OpenAI-Compatible
  tags_raw:
  - LLM
  - Inference
  - OpenAI Compatible
  properties:
  - type: Documentation
    url: https://developer.furiosa.ai/latest/en/furiosa_llm/furiosa-llm-serve.html
  - type: APIReference
    url: https://developer.furiosa.ai/latest/en/furiosa_llm/reference.html
  - type: Authentication
    url: authentication/furiosa-authentication.yml
  - type: Conventions
    url: conventions/furiosa-conventions.yml
  - type: RateLimits
    url: rate-limits/furiosa-rate-limits.yml
- aid: furiosa:furiosa-health-api
  name: FuriosaAI Health API
  description: The Health API from FuriosaAI — 2 operation(s) for health.
  humanURL: https://developer.furiosa.ai/latest/en/furiosa_llm/furiosa-llm-serve.html
  baseURL: http://{furiosa_llm_host}:8000/v1
  tags:
  - Health
  properties:
  - type: OpenAPI
    url: openapi/furiosa-health-api-openapi.yml
  - type: Protobuf
    url: grpc/furiosa-predict.proto
  - type: ErrorCatalog
    url: errors/furiosa-problem-types.yml
  - type: DataModel
    url: data-model/furiosa-data-model.yml
  - type: SourceCode
    url: https://github.com/furiosa-ai/furiosa-sdk
  - type: Protobuf
    url: grpc/furiosa-model-repository.proto
- aid: furiosa:furiosa-models-api
  name: FuriosaAI Models API
  description: The Models API from FuriosaAI — 3 operation(s) for models.
  humanURL: https://developer.furiosa.ai/latest/en/furiosa_llm/furiosa-llm-serve.html
  baseURL: http://{furiosa_llm_host}:8000/v1
  tags:
  - Models
  properties:
  - type: OpenAPI
    url: openapi/furiosa-models-api-openapi.yml
  - type: Protobuf
    url: grpc/furiosa-predict.proto
  - type: ErrorCatalog
    url: errors/furiosa-problem-types.yml
  - type: DataModel
    url: data-model/furiosa-data-model.yml
  - type: SourceCode
    url: https://github.com/furiosa-ai/furiosa-sdk
  - type: Protobuf
    url: grpc/furiosa-model-repository.proto
- aid: furiosa:furiosa-predict-api-api
  name: FuriosaAI Predict API
  description: The Predict API API from FuriosaAI — 1 operation(s) for predict api.
  humanURL: https://developer.furiosa.ai/latest/en/furiosa_llm/furiosa-llm-serve.html
  baseURL: http://{furiosa_llm_host}:8000/v1
  tags:
  - Predict API
  properties:
  - type: OpenAPI
    url: openapi/furiosa-predict-api-api-openapi.yml
  - type: Protobuf
    url: grpc/furiosa-predict.proto
  - type: ErrorCatalog
    url: errors/furiosa-problem-types.yml
  - type: DataModel
    url: data-model/furiosa-data-model.yml
  - type: SourceCode
    url: https://github.com/furiosa-ai/furiosa-sdk
  - type: Protobuf
    url: grpc/furiosa-model-repository.proto
- aid: furiosa:furiosa-repository-api
  name: FuriosaAI Repository API
  description: The Repository API from FuriosaAI — 3 operation(s) for repository.
  humanURL: https://developer.furiosa.ai/latest/en/furiosa_llm/furiosa-llm-serve.html
  baseURL: http://{furiosa_llm_host}:8000/v1
  tags:
  - Repository
  properties:
  - type: OpenAPI
    url: openapi/furiosa-repository-api-openapi.yml
  - type: Protobuf
    url: grpc/furiosa-predict.proto
  - type: ErrorCatalog
    url: errors/furiosa-problem-types.yml
  - type: DataModel
    url: data-model/furiosa-data-model.yml
  - type: SourceCode
    url: https://github.com/furiosa-ai/furiosa-sdk
  - type: Protobuf
    url: grpc/furiosa-model-repository.proto
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: License
  name: Apache-2.0
  url: https://github.com/furiosa-ai/furiosa-sdk/blob/main/LICENSE
- type: Overlay
  url: overlays/furiosa-predict-v2-overlay.yaml
- type: Overlay
  url: overlays/furiosa-model-repository-v2-overlay.yaml
- type: Website
  url: https://furiosa.ai/
- type: DeveloperPortal
  url: https://developer.furiosa.ai/latest/en/
- type: Documentation
  url: https://developer.furiosa.ai/latest/en/
- type: APIReference
  url: https://developer.furiosa.ai/latest/en/furiosa_llm/reference.html
- type: GettingStarted
  url: https://developer.furiosa.ai/latest/en/get_started/furiosa_llm.html
- type: Support
  url: https://furiosa-ai.atlassian.net/servicedesk/customer/portals
- type: Community
  url: https://forums.furiosa.ai/
- type: Blog
  url: https://furiosa.ai/blog
- type: GitHubOrganization
  url: https://github.com/furiosa-ai
- type: Roadmap
  url: https://developer.furiosa.ai/latest/en/overview/roadmap.html
- type: ChangeLog
  url: https://developer.furiosa.ai/latest/en/whatsnew/index.html
- type: SignUp
  url: https://lp.furiosa.ai/furiosa-access-program
- type: PrivacyPolicy
  url: https://furiosa.ai/privacy-policy
- type: Contact
  url: https://furiosa.ai/contact
- type: Packages
  url: packages/furiosa-packages.yml
- type: SDKs
  url: packages/furiosa-packages.yml
- type: CLI
  url: cli/furiosa-cli.yml
- type: Sandbox
  url: sandbox/furiosa-sandbox.yml
- type: Authentication
  url: authentication/furiosa-authentication.yml
- type: Conventions
  url: conventions/furiosa-conventions.yml
- type: ErrorCatalog
  url: errors/furiosa-problem-types.yml
- type: Lifecycle
  url: lifecycle/furiosa-lifecycle.yml
- type: Deprecation
  url: lifecycle/furiosa-lifecycle.yml
- type: Conformance
  url: conformance/furiosa-conformance.yml
- type: DataModel
  url: data-model/furiosa-data-model.yml
- type: DomainSecurity
  url: security/furiosa-domain-security.yml
- type: LLMsTxt
  url: llms/furiosa-llms.txt
- type: AgentSkill
  url: skills/_index.yml
- type: Plans
  url: plans/furiosa-plans-pricing.yml
- type: RateLimits
  url: rate-limits/furiosa-rate-limits.yml
- type: ChangeLog
  url: changelog/furiosa-changelog.yml
x-enrichment:
  date: '2026-08-16'
  status: enriched
  artifacts_added: 26
  pass: local-v1
x-base-url-note: All three baseURL values are TEMPLATED on purpose, not missing. FuriosaAI operates no hosted API; both HTTP
  surfaces are servers the customer starts on their own machine. The published defaults are http://localhost:8000/v1 for `furiosa-llm
  serve` and ports 8080 (REST) / 8081 (gRPC) for furiosa-server. repair-api-bases.py reports `no-usable-base` for this repo,
  which is the correct and expected reading of a self-hosted product rather than a defect to repair.
x-contract-discovery:
  date: '2026-08-16'
  openapi_on_api_hosts: /openapi.json, /openapi.yaml, /swagger.json and /api-docs all returned 404 on furiosa.ai and developer.furiosa.ai;
    api.furiosa.ai and docs.furiosa.ai do not resolve. The two OpenAPI documents in this repo were found instead in FuriosaAI's
    own GitHub repository at furiosa-ai/furiosa-sdk/python/furiosa-server/openapi/.
  ownership_note: 'Ownership check on those two specs. Their info.title reads "Predict API" and "Model Repository" and info.description
    points at kubeflow/kfserving and triton-inference-server rather than at FuriosaAI, and servers[] is empty. They are nonetheless
    FuriosaAI''s published contract: the furiosa-server README in the same first-party repository states the server is "compliant
    with KFServing''s V2 Dataplane specification and Triton''s Model Repository specification" and lists "OpenAPI specification
    support" as a shipped feature, so the specs describe FuriosaAI''s own product implementing a borrowed protocol verbatim
    - the same reason the .proto files carry upstream provenance headers.'
  graphql: No GraphQL surface exists or is documented.
  mcp: No MCP server, hosted or stdio, in 158 public repos or any registry. The developer center's only MCP mention is negative
    - the Responses API page states mcp built-in tools are not supported.
  a2a: /.well-known/agent-card.json and /.well-known/agent.json returned 404 on all three hosts.
  llms_txt: /llms.txt returned 404 on furiosa.ai and developer.furiosa.ai.

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