Arize Phoenix
by Arize AI
At a glance
Source-available AI observability project for tracing model calls, retrieval and tool execution.
eval developer-tools
- Licence
- Not recorded
- Category
- Platforms & Infrastructure
- Business model
- Free
- Availability
- Not recorded
- Launched
- Not recorded
Overview
Typical uses include Investigation of agent failures; Regression evaluation of AI applications. Documented capabilities: OpenTelemetry traces for LLM and agent steps; Evaluation of outputs and retrieval quality; Inspection of datasets, prompts and experiments.
Compare this tool Suggest a correction
Key features
- OpenTelemetry traces for LLM and agent steps
- Evaluation of outputs and retrieval quality
- Inspection of datasets, prompts and experiments
Use cases
- Investigation of agent failures
- Regression evaluation of AI applications
Pricing
Phoenix can be run on your infrastructure under Elastic License 2.0; its source availability is not an unrestricted open-source license. Infrastructure and evaluator-model costs are separate, and managed Arize offerings have separate commercial terms.
Record details
Provenance, dates and links are kept here so the main sections stay about the product itself.
Links, dates and provenance
- Record updated
- 2026-11-03
- Pricing
- arize.com ↗
- Documentation
- arize.com ↗
Selection profile
Every field says where its value comes from. "Unknown" means we have not confirmed it — it does not mean the product lacks the feature.
Selection profile11 fields6 unknown
- Tasks it fits
- Data analysis
Editorial classification of the documented features; not a product-performance test.
Suggest a correction - How you use it
- Web app
Editorial classification of the documented features; not a product-performance test.
Suggest a correction - Runs on
- Web
Editorial classification of the documented features; not a product-performance test.
Suggest a correction - Where it runs
- Self-hosted
Editorial classification of the documented features; not a product-performance test.
Suggest a correction - Works offline
- Not recorded
This product-specific field was not established in this entry’s source review.
Suggest a correction - Official service region
- Not recorded
This product-specific field was not established in this entry’s source review.
Suggest a correction - Public API
- Not recorded
This product-specific field was not established in this entry’s source review.
Suggest a correction - Licence
- Not recorded
This product-specific field was not established in this entry’s source review.
Suggest a correction - Commercial use
- Not recorded
This product-specific field was not established in this entry’s source review.
Suggest a correction - Interface languages
- Not recorded
This product-specific field was not established in this entry’s source review.
Suggest a correction - Billing
- Free Free allowance: Yes Subscription required: No
Prices are the vendor’s advertised entry price and exclude taxes; always confirm on the vendor’s own page.
Suggest a correction
Where each value comes from
- Tasks it fits
- Our inference
- How you use it
- Our inference
- Runs on
- Our inference
- Where it runs
- Our inference
- Works offline
- Unknown
- Official service region
- Unknown
- Public API
- Unknown
- Licence
- Unknown
- Commercial use
- Unknown
- Interface languages
- Unknown
Key facts and their evidence
Each fact lists the conditions it holds under, the page it was read from and the day it was checked.
-
Capability: OpenTelemetry traces for LLM and agent steps Verified 2026-11-03 arize.com ↗
Suggest a correction
Frequently asked questions
Where does Arize Phoenix fit in a workflow?
Source-available AI observability project for tracing model calls, retrieval and tool execution. OpenTelemetry traces for LLM and agent steps.
What costs and limits should I compare before choosing Arize Phoenix?
Phoenix can be run on your infrastructure under Elastic License 2.0; its source availability is not an unrestricted open-source license. Infrastructure and evaluator-model costs are separate, and managed Arize offerings have separate commercial terms.
Similar products
- Braintrust — Agent observability and evaluation platform that links production traces to quality experiments.
- CoreWeave Forge — AI development environment incorporating Weights & Biases experiment tracking, Weave evaluations and model lifecycle services.
- Evidently AI — Python evaluation framework for monitoring data quality, predictive models and LLM applications.
- Giskard — AI evaluation and red-teaming platform for finding security and business failures in agents.
- Helicone — LLM gateway and observability platform for inspecting requests, sessions and application costs.
- Langfuse — LLM engineering platform connecting agent traces, prompt versions and evaluations.
All Arize Phoenix alternatives → · All Platforms & Infrastructure products →
Sources
- Arize Phoenix — official product ↗
- Arize Phoenix — official documentation and terms ↗
- Arize Phoenix — official documentation and terms ↗
This record was last reviewed on 2026-11-03.
Machine-readable record: /api/products/arize-phoenix.json · Spot an error? Suggest a correction