# Portkey vs ZenML

**Leader by vioscaleAI score:** Portkey

| Attribute | Portkey | ZenML |
|---|---|---|
| **vioscaleAI score** | 78.9 (74% (medium)) | 60.8 (52% (medium)) |
| activity.commits_last_30d | - | 41 |
| adoption.dependent_repos | - | 44 |
| adoption.github_stars | - | 5,615 |
| content.faq | `[{"answer":"Portkey is an AI gateway platform that routes to 1,600+ language models while incorporating 50+ built-in content safety guardrails. It provides SDKs, CLI tools, and infrastructure components for deploying and managing generative AI applications. It is indexed under MLOps & LLMOps Tools.","source":"https://portkey.ai","question":"What is Portkey?","confidence":0.6},{"answer":"Portkey offers a free tier, so you can start without paying. Paid plans start at $9. Prices are published openly on the vendor's own pricing page. Pricing changes often, so verify at source before relying on it.","source":"https://portkey.ai/pricing","question":"Is Portkey free?","confidence":0.6},{"answer":"Portkey supports the web and a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.","source":"https://portkey.ai","question":"What platforms does Portkey support?","confidence":0.6},{"answer":"Yes. Portkey can be deployed cloud / SaaS and self-hosted, so it does not have to run on the vendor's infrastructure.","source":"https://portkey.ai","question":"Can Portkey be self-hosted?","confidence":0.6},{"answer":"We have confirmed 13 integrations for Portkey, including OpenAI, Google Cloud (Vertex AI, Gemini), Azure, AWS, GCP, Langgraph, CrewAI and Strands Agents, plus 5 more. This is what we could verify from public sources, so the vendor may support others we have not indexed.","source":"https://portkey.ai","question":"What does Portkey integrate with?","confidence":0.6},{"answer":"We have independently confirmed SOC 2, ISO 27001, HIPAA and GDPR for Portkey. Certifications we do not list are ones we have not been able to verify from public sources, which is not the same as Portkey not holding them. Always confirm compliance directly before you rely on it.","source":"https://portkey.ai/features/security-compliance","question":"What security certifications does Portkey have?","confidence":0.7}]` | `[{"answer":"An MLOps framework that provides reproducible machine learning pipelines with automatic logging, versioning, and observability. Includes agent runtime capabilities (Kitaru) for building replayable agent workflows, deployable on your existing infrastructure without vendor lock-in. It is indexed under MLOps & LLMOps Tools.","source":"https://www.zenml.io/blog/crewai-pricing","question":"What is ZenML?","confidence":0.6},{"answer":"ZenML is open source, so it can be self-hosted and used at no licence cost. It is released under the Apache-2.0 licence. Paid editions are also offered: Pro, priced on request. Pricing changes often, so verify at source before relying on it.","source":"https://www.zenml.io/blog/crewai-pricing","question":"Is ZenML free to use?","confidence":0.6},{"answer":"ZenML supports the web and a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.","source":"https://www.zenml.io/blog/crewai-pricing","question":"What platforms does ZenML support?","confidence":0.6},{"answer":"Yes. ZenML can be deployed cloud / SaaS, hybrid, on-premise and self-hosted, so it does not have to run on the vendor's infrastructure.","source":"https://www.zenml.io/blog/crewai-pricing","question":"Can ZenML be self-hosted?","confidence":0.6},{"answer":"We have confirmed 4 integrations for ZenML, including Git, Kubernetes, Docker and Poetry. This is what we could verify from public sources, so the vendor may support others we have not indexed.","source":"https://www.zenml.io/blog/crewai-pricing","question":"What does ZenML integrate with?","confidence":0.6},{"answer":"We have independently confirmed SOC 2 and ISO 27001 for ZenML. Certifications we do not list are ones we have not been able to verify from public sources, which is not the same as ZenML not holding them. Always confirm compliance directly before you rely on it.","source":"https://www.zenml.io","question":"What security certifications does ZenML have?","confidence":0.48},{"answer":"Yes. ZenML is published under the Apache-2.0 licence, a permissive licence that generally allows commercial use and modification. Licence terms can change between releases, so verify against the repository for the version you intend to use.","source":"https://github.com/zenml-io/zenml","question":"Is ZenML open source?","confidence":0.95}]` |
| deployment.options | `{"cloud":true,"hybrid":true,"on_prem":true,"self_hosted":true}` | `{"cloud":true,"hybrid":true,"self_hosted":true}` |
| description.long | Platform providing API gateway functionality, observability with logging and traces, safety guardrails, access governance, and prompt version management for teams deploying AI applications at scale. | ZenML is a Python-based orchestration framework that manages machine learning pipelines and agents across any infrastructure, from local development to production Kubernetes clusters. It provides centralized artifact management, automated tracking and versioning, and enterprise-grade security compliance for reproducible AI systems. |
| features.capabilities | `{"role":"gateway","caching":"semantic","evaluation":true,"open_source":true,"soc2_type_ii":true,"managed_cloud":true,"model_serving":true,"pricing_model":"pay_per_10k_traces","rate_limiting":true,"self_hostable":true,"multi_provider":true,"vpc_deployment":true,"deployment_model":"managed-SaaS","no_train_on_data":"unknown","routing_strategy":"load-based","llm_observability":true,"prompt_management":true,"architecture_model":"managed_cloud_saas","automatic_failover":true,"framework_agnostic":true,"experiment_tracking":true,"budget_spend_controls":true,"guardrails_moderation":"via-integration","openai_compatible_api":true,"virtual_key_management":true,"request_cost_observability":true,"mit_or_apache_permissive_oss_license":true,"production_ab_testing_of_system_prompts":true,"token_cost_and_latency_waterfall_charts":true,"pii_redaction_and_prompt_content_masking":true,"prompt_playground_and_in_dashboard_replay":true,"multi_step_agentic_workflow_distributed_tracing":true,"user_feedback_score_api_for_thumbs_up_down_tags":true,"native_integration_with_langchain_and_llamaindex":true}` | `{"role":"platform","evaluation":true,"managed_cloud":true,"model_serving":true,"self_hostable":true,"multi_provider":true,"vpc_deployment":true,"otel_compatible":true,"llm_observability":true,"prompt_management":true,"framework_agnostic":true,"experiment_tracking":true}` |
| integrations.count | 1,600 | 60 |
| integrations.list | `[{"name":"OpenAI"},{"name":"Google Cloud (Vertex AI, Gemini)"},{"name":"Azure"},{"name":"AWS"},{"name":"GCP"},{"name":"Langgraph"},{"name":"CrewAI"},{"name":"Strands Agents"},{"name":"Google ADK"},{"name":"Anthropic"},{"name":"Claude"},{"name":"Mistral"},{"name":"Google"},{"name":"MongoDB"},{"name":"Vertex AI"},{"name":"Claude Code","native":true}]` | `[{"name":"Git"},{"name":"GitHub"},{"name":"GitLab"},{"name":"Kubernetes"},{"name":"Docker"},{"name":"Poetry"},{"name":"Slack","native":true,"category":"chat","direction":"bidirectional"},{"name":"ClickUp","native":true,"category":"project management","direction":"bidirectional"},{"name":"MLflow","native":true,"category":"experiment tracking","direction":"outbound"},{"name":"Databricks","native":true,"category":"data platform","direction":"bidirectional"},{"name":"Trackio","native":true,"category":"experiment tracking","direction":"outbound"},{"name":"OpenAI","native":true,"category":"LLM provider","direction":"bidirectional"},{"name":"LangGraph","native":true,"category":"workflow framework","direction":"bidirectional"},{"name":"PyTorch","native":true,"category":"ML framework","direction":"bidirectional"},{"name":"scikit-learn","native":true,"category":"ML framework","direction":"bidirectional"},{"name":"Hugging Face","native":true,"category":"model hub","direction":"bidirectional"},{"name":"LlamaIndex","native":true,"category":"RAG framework","direction":"bidirectional"},{"name":"PyTorch Lightning","native":true,"category":"ML framework","direction":"bidirectional"},{"name":"Axolotl","native":true,"category":"ML framework","direction":"bidirectional"},{"name":"AzureML","native":true,"category":"ML service","direction":"bidirectional"},{"name":"AWS","native":true,"category":"cloud provider","direction":"bidirectional"},{"name":"Google Cloud","native":true,"category":"cloud provider","direction":"bidirectional"},{"name":"Azure","native":true,"category":"cloud provider","direction":"bidirectional"},{"name":"DigitalOcean","native":true,"category":"cloud provider","direction":"bidirectional"},{"name":"Kubeflow","native":true,"category":"ML orchestration","direction":"bidirectional"},{"name":"MySQL","native":true}]` |
| language.primary | - | Python |
| license.spdx | - | Apache-2.0 |
| market.availability | `{"primaryMarkets":[],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` | `{"primaryMarkets":["US"],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` |
| platform.support | `{"cli":true,"web":true}` | `{"cli":true,"mac":true,"linux":true,"windows":true}` |
| pricing | `{"type":"hybrid","plans":[{"free":true,"name":"Developer","summary":"Free forever, 10k logs/month","features":["Universal API & Key Management","Routing, Fallbacks, Load Balancing, Retries","3 Prompt Templates with Playground, Versioning, Variables","Logs, Traces, Feedback, Custom Metadata, Filters","Simple Caching","Deterministic Guardrails","Community Support","3 days log retention, 30 days metrics retention"],"components":[{"kind":"fixed","amount":0,"period":"month","currency":"USD"}],"description":"Free tier for prototyping and testing; not suitable for production workloads","contactSales":false,"includedLimits":{"recorded_logs":"10k/month"}},{"free":false,"name":"Production","summary":"$49/month + $9 per 100k request overage","features":["Universal API, Fallbacks, Load Balancing, Retries","Unlimited Prompt Templates with Playground, API Deployment, Versioning, Variables","Logs, Traces, Feedback, Metadata, Filters, Alerts","LLM & Partner Guardrails","Role-Based Access Control, Service Account API Keys","Simple & Semantic Caching","Production Support","30 days log retention, 90 days metrics retention"],"commitment":"monthly","components":[{"kind":"fixed","amount":49,"period":"month","currency":"USD"},{"per":{"qty":100000,"unit":"requests"},"kind":"metered","amount":9,"currency":"USD"}],"description":"For teams deploying LLM apps to production","contactSales":false,"includedLimits":{"recorded_logs":"100k/month"}},{"free":false,"name":"Enterprise","summary":"Custom pricing","features":["Custom retention periods for logs and metrics","Advanced Evaluation Templates with custom guardrail hooks","Role-Based Access Control, SSO (Okta), Granular Budget & Rate Limits","Private Cloud Deployment, VPC Hosting, Data Export to Data Lakes","SOC2 Type 2, GDPR, HIPAA compliance certifications","Custom Business Associate Agreements","Data Isolation, Configurable exports to data lakes","Dedicated Onboarding & Priority Support"],"description":"For organizations with complex compliance and high-volume production requirements","contactSales":true,"includedLimits":{"recorded_logs":"10M+/month"}}],"summary":"Free tier with 10k logs/month. Production at $49/month with usage overages. Enterprise custom pricing for compliance-focused organizations.","currency":"USD","freeTier":true,"sourceUrl":"https://portkey.ai/pricing","retrievedAt":"2026-08-21T13:46:13.229Z","startingPrice":{"amount":49,"period":"month","currency":"USD"},"billingPeriods":["month"]}` | `{"type":"hybrid","plans":[{"free":true,"name":"Community","summary":"Free, self-hosted","features":["experiment tracking","pipeline orchestration","artifact storage","model versioning"],"description":"Open-source self-hosted version with no license cost","contactSales":false},{"free":false,"name":"Pro","summary":"Managed service pricing not specified","features":["managed control plane","governance","SSO","SLA support","audit trails"],"description":"Managed cloud service with governance and SSO features","contactSales":false}],"summary":"Free open-source version; managed Pro service available","currency":"USD","freeTier":true,"sourceUrl":"https://www.zenml.io/blog/clearml-pricing","retrievedAt":"2026-09-10T21:07:20.688Z","billingPeriods":["month"]}` |
| pricing.free_tier | yes | yes |
| pricing.model | freemium | commercial |
| pricing.price_level | mid | low |
| pricing.starting_price | `{"amount":49,"currency":"USD"}` | - |
| pricing.transparent | yes | no |
| release.cadence_days | - | 15 |
| release.history | - | `[{"url":"https://github.com/zenml-io/zenml/releases/tag/0.97.0","date":"2026-09-23T13:30:23Z","type":"stable","version":"0.97.0"},{"url":"https://github.com/zenml-io/zenml/releases/tag/0.96.4","date":"2026-09-04T13:32:22Z","type":"stable","version":"0.96.4"},{"url":"https://github.com/zenml-io/zenml/releases/tag/0.96.3","date":"2026-08-07T13:24:25Z","type":"stable","version":"0.96.3"},{"url":"https://github.com/zenml-io/zenml/releases/tag/0.96.2","date":"2026-07-17T11:21:15Z","type":"stable","version":"0.96.2"},{"url":"https://github.com/zenml-io/zenml/releases/tag/0.96.1","date":"2026-07-02T20:38:13Z","type":"stable","version":"0.96.1"},{"url":"https://github.com/zenml-io/zenml/releases/tag/0.96.0","date":"2026-07-02T12:52:05Z","type":"stable","version":"0.96.0"},{"url":"https://github.com/zenml-io/zenml/releases/tag/0.95.1","date":"2026-06-18T12:24:26Z","type":"stable","version":"0.95.1"},{"url":"https://github.com/zenml-io/zenml/releases/tag/0.95.0","date":"2026-06-17T15:08:22Z","type":"stable","version":"0.95.0"},{"url":"https://github.com/zenml-io/zenml/releases/tag/0.94.6","date":"2026-06-02T10:57:18Z","type":"stable","version":"0.94.6"},{"url":"https://github.com/zenml-io/zenml/releases/tag/0.94.5","date":"2026-05-29T10:10:53Z","type":"stable","version":"0.94.5"},{"url":"https://github.com/zenml-io/zenml/releases/tag/0.94.4","date":"2026-05-12T15:13:19Z","type":"stable","version":"0.94.4"},{"url":"https://github.com/zenml-io/zenml/releases/tag/0.94.3","date":"2026-04-24T13:55:54Z","type":"stable","version":"0.94.3"},{"url":"https://github.com/zenml-io/zenml/releases/tag/0.94.2","date":"2026-04-08T15:00:24Z","type":"stable","version":"0.94.2"},{"url":"https://github.com/zenml-io/zenml/releases/tag/0.94.1","date":"2026-03-19T17:11:55Z","type":"stable","version":"0.94.1"},{"url":"https://github.com/zenml-io/zenml/releases/tag/0.94.0","date":"2026-03-04T18:22:00Z","type":"stable","version":"0.94.0"},{"url":"https://github.com/zenml-io/zenml/releases/tag/0.93.3","date":"2026-02-19T09:59:12Z","type":"stable","version":"0.93.3"},{"url":"https://github.com/zenml-io/zenml/releases/tag/0.93.2","date":"2026-01-29T22:30:18Z","type":"stable","version":"0.93.2"},{"url":"https://github.com/zenml-io/zenml/releases/tag/0.93.1","date":"2026-01-14T09:20:00Z","type":"stable","version":"0.93.1"},{"url":"https://github.com/zenml-io/zenml/releases/tag/0.93.0","date":"2025-12-16T09:19:32Z","type":"stable","version":"0.93.0"},{"url":"https://github.com/zenml-io/zenml/releases/tag/0.92.0","date":"2025-12-02T06:42:19Z","type":"stable","version":"0.92.0"}]` |
| reliability.status_page | yes | yes |
| security.certifications | `[{"name":"SOC2 Type II","level":"Type II","status":"active"},{"name":"ISO 27001","status":"active"},{"name":"GDPR","status":"active"},{"name":"HIPAA","status":"active"}]` | `[{"name":"SOC 2 Type II","level":"Type II","status":"active"},{"name":"ISO 27001","status":"active"}]` |
| security.gdpr | yes | - |
| security.hipaa | yes | - |
| security.iso27001 | yes | yes |
| security.scorecard | - | 6.8 |
| security.soc2 | yes | yes |
| security.trust_center | https://portkey.ai/features/security-compliance | https://www.zenml.io/blog/navigating-ofgem-compliance-for-ml-systems-in-energy-a-practical-guide |
| security.vulnerabilities | - | `{"count":14,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=zenml&per_page=100","last_12m":0,"max_severity":"CRITICAL"}` |

## Capabilities (MLOps & LLMOps Tools)

| Capability | Portkey | ZenML |
|---|:--:|:--:|
| **Core** |  |  |
| Tool role | Model gateway / router | End-to-end ML platform |
| **Deployment** |  |  |
| Self-hostable / OSS core | ✓ | ✓ |
| Managed cloud available | ✓ | ✓ |
| On-prem / VPC deployment | ✓ | ✓ |
| **Observability** |  |  |
| LLM tracing / observability | ✓ | ✓ |
| Evaluation (offline / LLM-judge / human) | ✓ | ✓ |
| **Dev** |  |  |
| Prompt management + versioning | ✓ | ✓ |
| **Tracking** |  |  |
| Experiment tracking / model registry | ✓ | ✓ |
| **Serving** |  |  |
| Model serving / inference endpoint | ✓ | ✓ |
| **Interop** |  |  |
| OpenTelemetry / OpenLLMetry compatible | - | ✓ |
| Framework-agnostic | ✓ | ✓ |
| **Gateway** |  |  |
| Multi-provider model support | ✓ | ✓ |
| **Data** |  |  |
| No-train-on-customer-data guarantee | Unknown | - |

*Source: vioscaleAI. Generated 2026-10-21T12:24:54.018Z. "-" = undocumented, not absent.*