PrefactorvsArizevsOpik

Arize vs Opik: how to choose

Both offer a free tool you can run yourself and a hosted cloud, and both trace agents, run experiments and version prompts. Opik's free self-hosted version includes online evaluation of production traffic under an Apache-2.0 licence; Arize keeps that in AX, its paid platform, now owned by Dynatrace.[3][4]

support-agent v4 · one run, two layersexample
Illustrative run, showing what each layer tells you
Arize / Opiksee
fetch_customer212ms · 1.2k tok
apply_refund1.4s · 3.1k tok
send_reply340ms · 0.8k tok
trace recorded, no verdict
Prefactoradds
Did its job✓ yes
Quality84 / 100
Cost$0.42 · in budget
Drift vs baselinenone
✓ a run that breaches its schema is held for review
§01 / THE SHORT ANSWERtl;dr: which, and when
TL;DR

What is the difference between Arize and Opik?

The main difference between Arize and Opik is what the free self-hosted version includes: Opik, from Comet, is Apache-2.0 and its self-hosted release scores production traffic with online evaluation rules, while Arize's free tool, Phoenix, is source-available and points to the paid AX platform for continuous production evals. Dynatrace completed its acquisition of Arize on 1 October 2026 and says Phoenix and AX continue. Comet remains independent.

The short answer

At a glance (checked 20 October 2026)

Decision factorArizeOpik
OwnershipAcquired by Dynatrace, completed 1 October 2026; Phoenix and AX continueComet ML, independent; reports $70M in total funding
LicencePhoenix: Elastic License 2.0 (source-available); AX: commercialApache-2.0 for the core platform and SDKs
Online evals in the free self-hosted versionNo; Phoenix docs point to AX for continuous production evalsYes, online evaluation rules on sampled traces, spans and threads
OpenTelemetryBuilt on it; Arize maintains the OpenInference conventionsOTLP over HTTP only; gRPC not supported
Run-time checksPartial: AX guards via Guardrails AI, run in your codePartial: guardrails your code calls; they fail closed
Free hosted tierAX Free: 25k spans a month, 15-day retention, unlimited usersFree Cloud: 25k spans a month, 60-day retention, up to 10 members
First paid tierAX Pro: $50 a month, 50k spans, 30-day retentionPro Cloud: $19 a month, 100k spans, then $5 per 100k
§02 / CAPABILITY MATRIXside by side: what each covers
Side by side

Arize vs Opik: capabilities side by side

CapabilityArizeOpikPrefactor
Observe
LLM call tracing✓✓✓
Multi-step agent tracing (tool calls, nested spans)✓✓✓
Cost tracking✓✓✓
OpenTelemetry support✓✓✓
Evaluate
Offline evals (datasets, experiments)✓✓✓
Online evals on production traffic✓✓✓
LLM-as-a-judge scoring✓✓✓
Code-based evaluators✓✓✓
Human review and annotation✓✓✓
Prompt versioning and playground✓✓—
Act on findings
Runtime controls on live agent actionsPartialPartial✓
Gateway or proxy in the request pathPartialPartial—
Licence and deployment
Open sourcePartial✓Partial
Self-hosting✓✓Partial
§03 / IN DEPTHdetail: the reasoning
In depth

What you get without paying

Opik's free self-hosted release scores live production traffic; Phoenix's does not. Opik self-hosts from the same Apache-2.0 repository as its cloud, with every feature except user administration, including online evaluation rules on sampled traces, spans and threads.

Read more

Phoenix covers tracing, datasets, experiments, LLM and code evaluators and prompt versioning; continuous evaluation, monitors and alerting belong to Arize AX. Phoenix uses the Elastic License 2.0, which forbids offering it to others as a hosted service, while Apache-2.0 sets no such limit. Opik's local Docker install is described as not production-ready; production deployments run on Kubernetes.

Arize has a new owner; Comet does not

Dynatrace completed its acquisition of Arize on 1 October 2026 and says it will keep supporting Phoenix and AX while integrating Arize into Dynatrace over time. Packaging and pricing may change, so time a large commitment with that in mind.

Read more

Comet ML, founded in 2017, reports $70M in total funding and has no ownership change on record as of 20 October 2026. Opik shipped steadily this year: Opik 2.0 with an environment-tagged Prompt Library in June, a per-evaluation judge spend cap in July and self-filling annotation queues in October.

Tracing, OpenTelemetry and run-time checks

Arize is built on OpenInference, its own OpenTelemetry conventions, while Opik accepts OTLP over HTTP only and does not state which conventions it reads. Teams already instrumented with OpenInference should test Opik's attribute mapping before switching.

Read more

AX adds Agent Trajectory, an automatic graph of which agents call which, for LangGraph, CrewAI, AG2 and others. Opik's SDKs cover Python, TypeScript, Java and .NET. On run-time checks the two are close: AX guards built on Guardrails AI run in your code and can return a default response, re-ask or raise an exception, and Opik's guardrails run as a blocking call your code handles, with English-only PII and topic checks. Neither offers approval holds on agent tool calls.

Pricing shape

Both price hosted plans on spans. As of 20 October 2026, AX Free gives 25k spans a month with 15-day retention and AX Pro is $50 a month for 50k spans with 30-day retention; Opik Free Cloud gives 25k spans with 60-day retention and Pro Cloud is $19 a month for 100k spans, then $5 per 100k.

Read more

AX Free has unlimited users, while Opik allows 10 members on Free and 50 on Pro. Self-hosted AX is Enterprise only, on quote; Phoenix and open-source Opik are free to run on your own infrastructure. Check Arize's pricing and Opik's pricing against your own volumes.

§04 / THE QUALITY GAPour take: where it stops
Our take

Where Prefactor fits

We sell the layer this section describes. Read it with that in mind.

Stated plainly, since Prefactor publishes this page: Prefactor is an agent evaluation platform that scores each step of a run, not only the final answer, and can act on a failing score through runtime policies, approval holds and a kill switch for a run, an agent or a team. Arize AX and Opik both offer guardrails that your own code calls, but neither documents approval holds or policies on agent tool calls. Prefactor has no prompt playground or prompt registry and its platform is hosted, so if free self-hosting or prompt iteration is the priority, Opik or Phoenix is the better fit. See the full comparison of 15 platforms.

See it on your own agents

A working session on a fleet like yours: watch a run evaluated, catch a drift, walk the record.

§05 / WHICH TO PICKdecide: by your stack
Which to pick

Which one fits

Pick Arize if

  • You run Dynatrace, or plan to, and want agent evaluation alongside it.
  • You want OpenInference at the centre of your instrumentation.
  • An agent trajectory graph across many agents matters to you.
  • You expect to pay for AX once you need continuous production evals and monitors.

Pick Opik if

  • You want online evals in a free, self-hosted deployment.
  • You want an Apache-2.0 licence with no restriction on how you host it.
  • A low first paid tier with 60-day retention suits your volumes.
  • You want automated prompt optimisation next to prompt versioning.
§06 / HOW WE REVIEWEDsources: checked October 20, 2026
Methodology

How we reviewed this comparison

Reviewed against public product and documentation pages on October 20, 2026. If a vendor has changed a feature, product name, or positioning since then, send a correction and we will update it. Numbered source links in the page body point to the ordered sources below.

Methodology

  • Reviewed public product, documentation, and launch material visible at the time of writing.
  • Mapped each page to the primary buyer, control layer, and runtime capabilities each vendor describes publicly.
  • Prefer direct product and documentation pages over analyst summaries or reseller material.
§07 / QUESTIONSfaq: the common ones
Questions
What is the difference between Arize and Opik?
Both trace LLM and agent applications, run experiments and version prompts, and both have a free self-hosted option. Opik's self-hosted version is Apache-2.0 and includes online evaluation rules. Arize splits its offer: Phoenix is source-available and self-hosted, and continuous production evals and monitoring sit in Arize AX, its paid platform.
How does Prefactor compare with Arize and Opik?
Prefactor is an agent evaluation platform for teams building AI agents: it observes every agent run from development to production, evaluates whether the agent did its job, and shows how to improve it. As of 20 October 2026, Prefactor can block or hold a live agent action; Arize and Opik do so in part. Arize and Opik both include prompt versioning and a playground. Prefactor evaluates how prompts perform in live runs rather than providing a prompt playground or registry.
Which free self-hosted option scores production traffic?
Opik. As of 20 October 2026, self-hosted Opik includes online evaluation rules that score sampled production traces, spans and threads. Phoenix's documentation points to Arize AX for continuous production evaluation.
Do Arize and Opik support OpenTelemetry?
Yes. Phoenix is built on OpenTelemetry and Arize maintains the OpenInference conventions, which both Phoenix and AX ingest. Opik accepts OTLP traces over HTTP only; gRPC is not supported, and the conventions it reads are not stated in its documentation.
What changes for Arize users after the Dynatrace acquisition?
Dynatrace completed the acquisition on 1 October 2026 and says Arize will keep supporting both Phoenix and AX, with Arize capabilities integrated into Dynatrace over time. Packaging may change, so check plans again before a large renewal.
Which has the larger free hosted tier?
They match on volume. As of 20 October 2026, AX Free and Opik Free Cloud both include 25k spans a month. AX Free keeps data for 15 days with unlimited users; Opik Free Cloud keeps it for 60 days for up to 10 team members.
Who owns Arize?
As of 20 October 2026: Dynatrace, which completed its acquisition of Arize on 1 October 2026. Dynatrace says Phoenix and AX will continue and that Arize capabilities will be integrated into Dynatrace over time.
Is Arize open source?
Partly. Phoenix's code is public under the Elastic License 2.0, which is source-available rather than open source: you can self-host and modify it but not offer it to others as a hosted service. AX is commercial.
How much does Arize cost?
As of 20 October 2026: AX Free is $0 for 25k spans a month with 15-day retention. AX Pro is $50 a month for 50k spans with 30-day retention. AX Enterprise is custom and is the only self-hosted AX option. Phoenix is free to self-host.
Can Arize block or hold a live agent action?
Partly. Arize AX documents guards built on the Guardrails AI framework that run in your own code around model calls. There is no documented approval or policy layer for agent tool actions.
Who owns Opik?
As of 20 October 2026: Comet ML, Inc., an independent company founded in 2017 that reports $70M in total funding.
Is Opik open source?
Yes. The core platform, including tracing, evaluation, the UI, backend and SDKs, is Apache-2.0 and free to self-host.
How much does Opik cost?
As of 20 October 2026: Self-hosting is free with unlimited spans. Free Cloud covers 25k spans a month and 10 users. Pro Cloud is $19 a month for 100k spans, then $5 per 100k. Enterprise is custom.
Can Opik block or hold a live agent action?
Partly. Opik guardrails run as a blocking check that your code must call and handle. There are no approval workflows for agent actions.
Is Prefactor open source?
Partly. Its deterministic evals package is Apache-2.0; the platform is hosted.
How much does Prefactor cost?
As of 20 October 2026: Dev is free with 5,000 spans a month. Startup is $49 a month and Scaleup $199 a month. Enterprise is custom above 4 million spans a month.
Can Prefactor block or hold a live agent action?
Yes. Runtime policies can block, throttle, sandbox or escalate an agent's tool calls and data access before they run, approval routing holds risky actions for a person, and a kill switch stops a run, an agent or a team.
Reviewed against public sources on October 20, 2026Suggest a correction

Score the run, then act on it

Prefactor scores each step of every agent run and can hold or stop an action when a score says it should not happen. Start on the free tier: 5,000 spans a month, no credit card required.

Agent Performance Platform
Unified performance platform for agents, authentication, and risk management
All Systems Operational
3Global Agents
7Instances
5Services
12%Human Intervene
4High Risk
$2,360Monthly Spend
Mission ControlLive agent health with 7-day activity heartbeat
Claims Proc...68
$330/moRed
Claims Proc...65
$160/moRed
Claims Proc...82
$170/moAmber
ChatGPT74
$150/moAmber

See how every agent performs, and make it better

Prefactor helps teams observe, evaluate, and improve their AI agents in production, across every framework and provider.