Arize Phoenix vs Vellum
Vellum scores higher on the AgentReady, 88/100 against 70/100. They differ on 10 of the 41 signals. Which ones decides whether an agent can adopt them without a person watching.
What each one is
Arize Phoenix. Arize Phoenix is an open-source AI engineering platform for self-improving agents, providing observability, evaluation, and learning capabilities for AI agents and applications.
Vellum. A personal AI assistant that lives in the secure Vellum Cloud, has its own identity, and actually does things in the world.
Where Arize Phoenix is ahead
Arize Phoenix passes agent compatibility verified, and Vellum does not. That is operate, whether an agent can run against it in production and recover when a call fails.
Where Vellum is ahead
Vellum passes openapi / spec quality, request examples provided, response examples provided and errors and status codes documented, and Arize Phoenix does not. That is understand, whether an agent can read the docs and work out how the API behaves before calling it.
It also holds adopt: no mandatory sales call, programmatic credential creation, fast time to first request and copyable quickstart. Arize Phoenix misses those.
And on operate, machine-readable errors. Arize Phoenix misses it.
What neither does
Both fail authentication documented, limits / constraints documented, idempotency support, rate-limit behavior predictable. If your agent needs any of those, you will be building it yourself either way.
Score, pillar by pillar
The AgentReady splits into four pillars, scored separately, because a product can be easy to find and still impossible to adopt.
Understand is whether an agent can read the docs and work out how the API behaves before calling it. Vellum leads 85 to 38. Arize Phoenix misses openapi / spec quality, authentication documented, request examples provided, response examples provided, errors and status codes documented, limits / constraints documented; Vellum misses authentication documented, limits / constraints documented.
Adopt. Vellum leads 100 to 70. Arize Phoenix misses no mandatory sales call, programmatic credential creation, fast time to first request, copyable quickstart; Vellum misses nothing.
Operate. Arize Phoenix leads 71 to 67. Arize Phoenix misses machine-readable errors, idempotency support, rate-limit behavior predictable; Vellum misses idempotency support, rate-limit behavior predictable, agent compatibility verified.
Pricing
Arize Phoenix does not publish a machine-readable starting price and has a free tier. Vellum starts at $30/mo and has a free tier.
| Arize Phoenix plans | Vellum plans |
|---|---|
| - | Mighty $30/month |
| - | Super $100/month |
| - | Ultra $200/month |
| - | Custom Plan Custom |
Signal by signal
| Signal | Arize Phoenix | Vellum |
|---|---|---|
| AgentReady | 70 | 88 |
| Discovery | 100 | 100 |
| Understanding | 38 | 85 |
| Adoption | 70 | 100 |
| Operability | 71 | 67 |
| Public API | Yes | Yes |
| MCP server | Yes | Yes |
| OpenAPI spec | Yes | Yes |
| CLI | Yes | Yes |
| llms.txt | Yes | Yes |
| Self-serve signup | Yes | Yes |
| Free tier | Yes | Yes |
Which to pick
Vellum clears more of the signals an agent needs, so it is the safer default for unattended use. Full profiles: Arize Phoenix and Vellum. Alternatives to each: Arize Phoenix, Vellum.
An agent can fetch this as data: POST /v1/compare {"slugs": ["arize", "vellum"]}