# Arize Phoenix

**Canonical:** https://apis.io/providers/phoenix/  
**Website:** https://arize.com/phoenix/  
**APIs profiled:** 17

Arize Phoenix is an open-source AI observability and evaluation platform built on OpenTelemetry, enabling developers to trace, evaluate, and debug LLM applications in production or locally. Phoenix exposes a REST API for programmatically ingesting spans and traces, managing datasets, running experiments, submitting annotations, and querying evaluation results. The platform supports a wide range of LLM frameworks including LangChain, LlamaIndex, OpenAI, Anthropic, and CrewAI through auto-instrumentation. Phoenix can be self-hosted in a single command or used as a managed cloud service (Arize AX), with authentication via API keys and OAuth2/OIDC for enterprise deployments.

## Kin Score — 39.8 / 100 (developing)

Scored 2026-08-25 under rubric 0.14.0. Trend: flat (+0.0 from 39.8).

| Facet | Score |
|---|---|
| Discoverability | 74.1 |
| Contract Quality | 56.3 |
| Governance | 9.8 |
| Contract Governance | 9.8 |
| Operational Transparency | 36.8 |
| Developer Ergonomics | 11.9 |
| Commercial Clarity | 50.0 |
| Access Clarity | 50.0 |

## Agent readiness — 25.5 (agent-aware)

| Dimension | Value |
|---|---|
| Spec Presence | yes |
| Agentic Access | derived |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | no |
| Idempotency | no |
| Error Semantics | verified |
| OpenAPI Examples | partial |
| Rate Limit Signal | documented |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |
| Delegated Identity | no |
| Protected Resource Metadata | no |
| Dynamic Client Registration | no |
| Agentic Commerce | no |

## Access

Freemium — onboarding: unknown, pricing: freemium, trial: no (confidence: medium).

## APIs (17)

- **Arize Phoenix annotation_configs API** — The annotation_configs API from Arize Phoenix — 3 operation(s) for annotation_configs.
- **Arize Phoenix annotations API** — The annotations API from Arize Phoenix — 3 operation(s) for annotations.
- **Arize Phoenix Arize Phoenix Version API** — The Arize Phoenix Version API from Arize Phoenix — 1 operation(s) for arize phoenix version.
- **Arize Phoenix Auth API** — The Auth API from Arize Phoenix — 6 operation(s) for auth.
- **Arize Phoenix chat API** — The chat API from Arize Phoenix — 2 operation(s) for chat.
- **Arize Phoenix datasets API** — The datasets API from Arize Phoenix — 9 operation(s) for datasets.
- **Arize Phoenix experiments API** — The experiments API from Arize Phoenix — 8 operation(s) for experiments.
- **Arize Phoenix Healthz API** — The Healthz API from Arize Phoenix — 1 operation(s) for healthz.
- **Arize Phoenix Oauth2 API** — The Oauth2 API from Arize Phoenix — 2 operation(s) for oauth2.
- **Arize Phoenix projects API** — The projects API from Arize Phoenix — 2 operation(s) for projects.
- **Arize Phoenix prompts API** — The prompts API from Arize Phoenix — 8 operation(s) for prompts.
- **Arize Phoenix Readyz API** — The Readyz API from Arize Phoenix — 1 operation(s) for readyz.
- **Arize Phoenix secrets API** — The secrets API from Arize Phoenix — 1 operation(s) for secrets.
- **Arize Phoenix sessions API** — The sessions API from Arize Phoenix — 5 operation(s) for sessions.
- **Arize Phoenix spans API** — The spans API from Arize Phoenix — 6 operation(s) for spans.
- **Arize Phoenix traces API** — The traces API from Arize Phoenix — 4 operation(s) for traces.
- **Arize Phoenix users API** — The users API from Arize Phoenix — 3 operation(s) for users.

## Agentic access (1)

- **Phoenix Agentic Access** — 84 operations · 43 acting · 2 human-in-the-loop

## Security (1)

- **Phoenix Domain Security** — TLSv1.3 · HSTS · DNSSEC · DMARC

## Plans (1)

- **Phoenix Plans Pricing**

## Tags

LLM Observability, AI Evaluation, OpenTelemetry, Tracing, LLMOps, AI Monitoring, Open-Source, Prompt Engineering, Datasets, Experiments

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/phoenix/). Scores are computed from the provider's own public artifacts under a published rubric.