Arize Phoenix
Open-source platform for monitoring and evaluating language model applications in production
- Vendor
- Arize
- Also known as
- arize-phoenix
What is Arize Phoenix?
A self-hosted platform that traces and evaluates language model application behavior using OpenTelemetry instrumentation, enabling teams to debug, optimize, and monitor LLM performance.
Arize Phoenix pricing
We don't have Arize Phoenix's full plan breakdown yet (its pricing page resisted automated reading). Here's what we could confirm. Always check live pricing for exact numbers.
Open-source and free
What Arize Phoenix does
The capabilities that matter for llm observability, normalised so it lines up with every alternative. “-” means we haven't confirmed it, not that it's missing.
- Architecture model
- Open source self hosted
- Token cost and latency waterfall charts
- ✓
- Opentelemetry openllmetry native export support
- ✓
- Prompt playground and in dashboard replay
- ✓
- Multi step agentic workflow distributed tracing
- ✓
- User feedback score API for thumbs up down tags
- -
- Pii redaction and prompt content masking
- -
- Production ab testing of system prompts
- ✓
- Automated anomaly detection for rate limits
- -
- Native integration with langchain and llamaindex
- ✓
- SOC2 type ii
- -
- Mit or apache permissive oss license
- -
- Pricing model
- Free open source
Platform & deployment
Independently observed- CLI
- Web
- Self-hosted
Integrations (19)
Independently observed- Gemini•
- LlamaIndex
- OpenAI
- Anthropic
- AWS Bedrock
- Vertex AI
- Claude Code
- Cursor
- OpenLLMetry
- OpenTelemetry•
- OpenInference
- Google Vertex AI•
- Google Gemini•
- Together AI•
- Fireworks•
- NVIDIA NIM•
- LiteLLM•
- LangChain•
- Traceloop•
Security & compliance
Known vulnerabilities: 0 (0 in the last 12 months) sourcea count reflects scale & disclosure, not quality
Arize Phoenix FAQ
Common questions about Arize Phoenix, answered from independent, dated evidence.
What is Arize Phoenix?
Phoenix provides OpenTelemetry-based instrumentation for LLM applications, AI-powered evaluation of model outputs and retrieval quality, and systematic prompt management with versioning. It supports both self-hosted and cloud deployment and integrates with major LLM frameworks and development tools. It is indexed under Llm Observability.
Source: https://phoenix.arize.com
Can Arize Phoenix be self-hosted?
Yes. Arize Phoenix can be deployed cloud / SaaS and self-hosted, so it does not have to run on the vendor's infrastructure.
Source: https://phoenix.arize.com
What does Arize Phoenix integrate with?
We have confirmed 8 integrations for Arize Phoenix, including LlamaIndex, OpenAI, Anthropic, AWS Bedrock, Vertex AI, Claude Code, Cursor and OpenLLMetry. This is what we could verify from public sources, so the vendor may support others we have not indexed.
Source: https://phoenix.arize.com
Arize Phoenix alternatives
Other llm observability we track, ranked by the same independent score.
- LunaryMonitor and analyze AI application performance with real-time insights and enterprise controlmedium · 73%
- TraceloopAn open-source Rust-based LLM gateway providing unified multi-provider access with built-in observabilitymedium · 72%
- OpikAn open-source platform for monitoring and evaluating AI applications and agent workflowslow · 29%
- Weights & Biases WeaveMonitoring and tracing for AI agents in production environmentslow · 25%
- AgentOpsMonitoring and observability platform for AI agents with cost tracking and performance debuggingmedium · 53%
Compare Arize Phoenix
Side by side against other llm observability, attribute by attribute, with a source on every value.
The vioscaleAI score: one lens on the evidence
Not user reviews and not a paid placement: a confidence-weighted blend of the independent signals below (adoption, activity, security posture, and more), which you can sort and re-weight yourself. Vendors can correct their listing but can never move their rank, and stars are weighted low as a vanity metric. It is one way to read the evidence for Arize Phoenix, not the verdict.
| Signal | Score | Weight | Contribution | Evidence |
|---|---|---|---|---|
| Development activity | 63 | 0.14 | 8.5 | ✓ |
| Capabilities | 81 | 0.08 | 6.5 | ✓ |
| Stars | 77 | 0.05 | 3.6 | ✓ |
| Integrations | 31 | 0.05 | 1.7 | ✓ |
| Dependent projects | 0 | 0.05 | 0.0 | ✓ |
| Release cadence | 0 | 0.08 | 0.0 | - |
| Security posture | 0 | 0.12 | 0.0 | - |
| Package downloads | 0 | 0.04 | 0.0 | - |
| Security score | 0 | 0.05 | 0.0 | - |
| Developer Q&A activity | 0 | 0.14 | 0.0 | - |
Computed . Re-weight it by intent, or see the full method.
All data & sourcesshow ↓
Every value we hold, with its source, retrieval date, and confidence. This is the evidence behind the score: don't trust it, verify it.
Activity
| Attribute | Value | Evidence |
|---|---|---|
| Commits last 30d | 100 | mediumsource · 2026-10-15 · 65% |
Adoption
Content
| Attribute | Value | Evidence |
|---|---|---|
| Faq | 3 items | mediumsource · 2026-09-10 · 60% |
Features
| Attribute | Value | Evidence |
|---|---|---|
| Capabilities | Pricing model: free_open_source · Architecture model: open_source_self_hosted · Production ab testing of system prompts: Yes · Token cost and latency waterfall charts: Yes · Prompt playground and in dashboard replay: Yes · Multi step agentic workflow distributed tracing: Yes | mediumsource · 2026-10-15 · 60% |
Integrations
| Attribute | Value | Evidence |
|---|---|---|
| Count | 11 | mediumsource · 2026-10-15 · 60% |
Language
| Attribute | Value | Evidence |
|---|---|---|
| Primary | Python | highsource · 2026-10-15 · 90% |
Pricing
Release
| Attribute | Value | Evidence |
|---|---|---|
| History | 20 items | mediumsource · 2026-10-15 · 70% |
Security
| Attribute | Value | Evidence |
|---|---|---|
| Vulnerabilities | Count: 0 · Source: https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=npm&package_name=%40arizeai%2Fphoenix-config&per_page=100 · Last 12m: 0 | highsource · 2026-10-15 · 90% |
Is Arize Phoenix the right choice for you?
Tell us the job, the constraints and what you weigh most, and we will rank Arize Phoenix against the rest of the llm observability we index, using the same dated evidence weighted your way.
Free to run, no account needed to start. How the evaluation works
Is this your product?
This profile was built from public sources without asking you. You can take the badge below and use it anywhere, and you can claim the profile to correct anything we got wrong. Both are free, and neither moves Arize Phoenix up or down: nobody can buy rank here, including you.
Take the badge
Live, always current, and free to use on your own site. It shows Arize Phoenix's independent score and links back to this profile.
<a href="https://www.vioscale.ai/software/arize-phoenix" target="_blank" rel="noopener">
<img src="https://www.vioscale.ai/badge/software/arize-phoenix.svg" alt="Arize Phoenix, verified on vioscaleAI" width="330" height="76" loading="lazy" />
</a>Markdown, for a README →
[](https://www.vioscale.ai/software/arize-phoenix)Claim the profile
Verify you control the domain, then point us at the pages that state the facts about Arize Phoenix and add your own description and media. Free, and it does not change the score.
- Correct anything wrong, with evidence
- Point our crawler at the pages that matter
- Write your own description and add media
Not the owner? How vendor profiles work