Tensordyne

Tensordyne (formerly Recogni) builds next-generation AI inference systems from the foundation up — a proprietary logarithmic-math architecture cast into custom 3nm silicon, compute hardware, scale-up interconnect, and system software. Its flagship Napier platform targets the fastest, lowest-cost, most energy-efficient generative AI inference for hyperscaler and neocloud data centers, delivering 608 PFLOPS dense compute per rack in an air-cooled 30 kW pod and supporting MoE models, agentic workloads, and 4K video generation. The stack integrates with PyTorch, Triton, vLLM, and Kubernetes; a developer SDK is announced as coming soon. Backed by Mayfield, Bosch Ventures, Toyota Ventures, GreatPoint Ventures, and Plug and Play, the company has raised more than $211M and operates from Sunnyvale, California and Munich, Germany.

Tensordyne is profiled on the APIs.io network. Tagged areas include Company, Artificial Intelligence, AI Inference, Semiconductors, and AI Hardware.

Tensordyne’s developer surface includes engineering blog, support, YouTube channel, and 8 more developer resources.

🌐 Visit website 📡 Source on GitHub
12.3/100 minimal ▬ flat Agent 0/100 human only Full breakdown ↓
scored 2026-07-27 · rubric v0.5
0 APIs
CompanyArtificial IntelligenceAI InferenceSemiconductorsAI HardwareData CenterMachine LearningSiliconGenerative AIDeep Learning

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 12.3/100 · minimal
Contract Quality 0.0 / 25
Developer Ergonomics 1.3 / 20
Commercial Clarity 4.2 / 20
Operational Transparency 0.0 / 13
Governance 0.0 / 12
Discoverability 6.8 / 10
Agent readiness — 0/100 · human only
Machine-Readable Contract 0 / 18
Agentic Access Contract 0 / 15
MCP Server 0 / 12
Machine-Readable Auth 0 / 10
Idempotency 0 / 9
Stable Error Semantics 0 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 0 / 7
Typed Event Surface 0 / 6
Agent Skills 0 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
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/tensordyne: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

Security Posture 1

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

Tensordyne Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Resources

Access & Security 1

Authentication, authorization, and security posture

DomainSecurity
DomainSecurity

Learn 1

Tutorials, courses, talks, and written guidance

YouTube
YouTube

Operate 1

Status, limits, changes, and where to get help

Support
Support

Commercial 2

Pricing, plans, and the legal terms of use

PrivacyPolicy
PrivacyPolicy
 TermsOfService
TermsOfService

Company 6

The organization behind the API

Website
Website
 About
About
 Blog
Blog
 Careers
Careers
 LinkedIn
LinkedIn
 Twitter
Twitter

Source (apis.yml)

apis.yml Raw ↑ 
aid: tensordyne
accessModel:
  pricing: unknown
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Unknown
  confidence: low
  source: []
  generated: '2026-07-22'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/tensordyne.png
name: Tensordyne
description: Tensordyne (formerly Recogni) builds next-generation AI inference systems from the foundation up — a proprietary
  logarithmic-math architecture cast into custom 3nm silicon, compute hardware, scale-up interconnect, and system software.
  Its flagship Napier platform targets the fastest, lowest-cost, most energy-efficient generative AI inference for hyperscaler
  and neocloud data centers, delivering 608 PFLOPS dense compute per rack in an air-cooled 30 kW pod and supporting MoE models,
  agentic workloads, and 4K video generation. The stack integrates with PyTorch, Triton, vLLM, and Kubernetes; a developer
  SDK is announced as coming soon. Backed by Mayfield, Bosch Ventures, Toyota Ventures, GreatPoint Ventures, and Plug and
  Play, the company has raised more than $211M and operates from Sunnyvale, California and Munich, Germany.
url: https://raw.githubusercontent.com/api-evangelist/tensordyne/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- mayfield
x-tier: stub
x-tier-reason: portfolio-lead
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-21'
tags:
- Company
- Artificial Intelligence
- AI Inference
- Semiconductors
- AI Hardware
- Data Center
- Machine Learning
- Silicon
- Generative AI
- Deep Learning
apis: []
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Website
  url: https://tensordyne.ai
- type: About
  url: https://www.tensordyne.ai/about
- type: Blog
  url: https://www.tensordyne.ai/stories
- type: Support
  url: https://www.tensordyne.ai/contact
- type: PrivacyPolicy
  url: https://www.tensordyne.ai/legal/privacy-policy
- type: TermsOfService
  url: https://www.tensordyne.ai/legal/terms-of-service
- type: Careers
  url: https://www.tensordyne.ai/careers
- type: LinkedIn
  url: https://www.linkedin.com/company/tensordyne
- type: Twitter
  url: https://x.com/TensordyneInc
- type: YouTube
  url: https://youtube.com/@TensordyneInc
- type: DomainSecurity
  url: security/tensordyne-domain-security.yml
x-enrichment:
  date: '2026-07-21'
  status: minimal
  artifacts_added: 1
  pass: local-v1