TensorZero

TensorZero is an open-source, self-hosted LLMOps platform that unifies five capabilities behind one stack: a high-performance LLM Gateway that accesses every major model provider (Anthropic, OpenAI, AWS Bedrock/SageMaker, Azure, GCP Vertex, Mistral, Groq, xAI and more) through a single OpenAI-compatible API with sub-millisecond p99 overhead; Observability that stores inferences and feedback in your own database; Evaluation via heuristics and LLM judges; Optimization of prompts, models, and inference strategies from metrics and human feedback; and Experimentation with built-in A/B testing, routing, retries, and fallbacks. Written in Rust and deployed as a single Docker container, it plays nicely with the OpenAI SDK and OpenTelemetry. NOTE: as of 2026 TensorZero is no longer maintained — the source remains available on GitHub (all org repositories archived) and the final Python client (2026.6.0) is on PyPI, but the hosted product has wound down.

TensorZero is profiled on the APIs.io network. Tagged areas include Company, Ai Ml, LLM, LLMOps, and AI Gateway.

TensorZero’s developer surface includes documentation, API reference, getting-started guide, engineering blog, support, changelog, authentication, and 13 more developer resources.

🌐 Visit website 📡 Source on GitHub

24.7/100 emerging ▬ flat Agent 14/100 human only Full breakdown ↓
scored 2026-07-27 · rubric v0.5

AccessSelf serve

0 APIs

CompanyAi MlLLMLLMOpsAI GatewayInferenceObservabilityOpen SourceModel Routing

Kin Score

Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5

Composite quality — 24.7/100 · emerging

Contract Quality 0.0 / 25

Developer Ergonomics 10.0 / 20

Commercial Clarity 4.2 / 20

Operational Transparency 3.8 / 13

Governance 0.0 / 12

Discoverability 6.8 / 10

Agent readiness — 14/100 · human only

Machine-Readable Contract 0 / 18

Agentic Access Contract 0 / 15

MCP Server 0 / 12

Machine-Readable Auth 10 / 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 4 / 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/tensorzero: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

Get Started 1

Portal, sign-up, and the first successful call

GettingStarted

GettingStarted

Documentation 2

Reference material describing how the API behaves

Documentation

Documentation

APIReference

APIReference

Agent Surfaces 2

MCP servers, agent skills, and machine-readable catalogs

WellKnown

WellKnown

LLMsTxt

LLMsTxt

Design & Contract 3

Pagination, idempotency, versioning, errors, and events

Conventions

Conventions

Conformance

Conformance

Lifecycle

Lifecycle

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

ChangeLog

ChangeLog

Deprecation

Deprecation

Commercial 2

Pricing, plans, and the legal terms of use

TermsOfService

TermsOfService

PrivacyPolicy

PrivacyPolicy

Company 2

The organization behind the API

Website

Website

Blog

Blog

Source (apis.yml)

aid: tensorzero
name: TensorZero
description: 'TensorZero is an open-source, self-hosted LLMOps platform that unifies five capabilities behind one stack: a
  high-performance LLM Gateway that accesses every major model provider (Anthropic, OpenAI, AWS Bedrock/SageMaker, Azure,
  GCP Vertex, Mistral, Groq, xAI and more) through a single OpenAI-compatible API with sub-millisecond p99 overhead; Observability
  that stores inferences and feedback in your own database; Evaluation via heuristics and LLM judges; Optimization of prompts,
  models, and inference strategies from metrics and human feedback; and Experimentation with built-in A/B testing, routing,
  retries, and fallbacks. Written in Rust and deployed as a single Docker container, it plays nicely with the OpenAI SDK and
  OpenTelemetry. NOTE: as of 2026 TensorZero is no longer maintained — the source remains available on GitHub (all org repositories
  archived) and the final Python client (2026.6.0) is on PyPI, but the hosted product has wound down.'
url: https://raw.githubusercontent.com/api-evangelist/tensorzero/refs/heads/main/apis.yml
accessModel:
  pricing: unknown
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Self-serve signup
  confidence: medium
  source:
  - authentication
  generated: '2026-07-22'
  method: derived
image: https://github.com/tensorzero.png
x-type: company
x-source: vc-portfolio
x-backed-by:
- bessemer-venture-partners
x-tier: stub
x-tier-reason: portfolio-lead
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-21'
tags:
- Company
- Ai Ml
- LLM
- LLMOps
- AI Gateway
- Inference
- Observability
- Open Source
- Model Routing
apis: []
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Website
  url: https://www.tensorzero.com/
- type: Documentation
  url: https://github.com/tensorzero/tensorzero/tree/main/docs
- type: APIReference
  url: https://www.tensorzero.com/docs/gateway/api-reference
- type: GettingStarted
  url: https://www.tensorzero.com/docs/quickstart
- type: Blog
  url: https://www.tensorzero.com/blog/
- type: GitHubOrganization
  url: https://github.com/tensorzero
- type: Support
  url: https://www.tensorzero.com/slack
- type: TermsOfService
  url: https://www.tensorzero.com/terms/
- type: PrivacyPolicy
  url: https://www.tensorzero.com/privacy/
- type: ChangeLog
  url: https://github.com/tensorzero/tensorzero/releases
- type: Packages
  url: packages/tensorzero-packages.yml
- type: SDKs
  url: packages/tensorzero-packages.yml
- type: Authentication
  url: authentication/tensorzero-authentication.yml
- type: Conventions
  url: conventions/tensorzero-conventions.yml
- type: Conformance
  url: conformance/tensorzero-conformance.yml
- type: Lifecycle
  url: lifecycle/tensorzero-lifecycle.yml
- type: Deprecation
  url: lifecycle/tensorzero-lifecycle.yml
- type: WellKnown
  url: well-known/tensorzero-well-known.yml
- type: DomainSecurity
  url: security/tensorzero-domain-security.yml
- type: LLMsTxt
  url: llms/tensorzero-llms.txt
x-enrichment:
  date: '2026-07-21'
  status: enriched
  artifacts_added: 8
  pass: local-v1