# MLflow vs Portkey

**Leader by vioscaleAI score:** Portkey

| Attribute | MLflow | Portkey |
|---|---|---|
| **vioscaleAI score** | 70.7 (68% (medium)) | 78.9 (76% (high)) |
| activity.commits_last_30d | 100 | - |
| adoption.dependent_repos | 5,089 | - |
| adoption.github_stars | 27,843 | - |
| adoption.package_downloads_weekly | 9,993,245 | - |
| content.faq | `[{"answer":"A comprehensive, open-source platform that provides experiment tracking, model registry, LLM tracing, prompt management, and deployment capabilities across the complete machine learning and AI lifecycle It is indexed under MLOps & LLMOps Tools.","source":"https://mlflow.org","question":"What is MLflow?","confidence":0.6},{"answer":"MLflow is open source, so it can be self-hosted and used at no licence cost. It is released under the Apache-2.0 licence. Pricing changes often, so verify at source before relying on it.","source":"https://mlflow.org","question":"Is MLflow free to use?","confidence":0.6},{"answer":"MLflow supports the web and a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.","source":"https://mlflow.org","question":"What platforms does MLflow support?","confidence":0.6},{"answer":"Yes. MLflow can be deployed cloud / SaaS and self-hosted, so it does not have to run on the vendor's infrastructure.","source":"https://mlflow.org","question":"Can MLflow be self-hosted?","confidence":0.6},{"answer":"We have confirmed 24 integrations for MLflow, including Databricks, AWS S3, Google Cloud Storage, Azure Storage, AzureML, Kubernetes, LangChain and Pydantic AI, plus 16 more. This is what we could verify from public sources, so the vendor may support others we have not indexed.","source":"https://mlflow.org","question":"What does MLflow integrate with?","confidence":0.6},{"answer":"Yes. MLflow 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/mlflow/mlflow","question":"Is MLflow open source?","confidence":0.95}]` | `[{"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}]` |
| deployment.options | `{"cloud":true,"self_hosted":true}` | `{"cloud":true,"self_hosted":true}` |
| description.long | A comprehensive, open-source platform that provides experiment tracking, model registry, LLM tracing, prompt management, and deployment capabilities across the complete machine learning and AI lifecycle | 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. |
| features.capabilities | `{"role":"platform","evaluation":true,"open_source":true,"managed_cloud":true,"model_serving":true,"pricing_model":"free_open_source","rate_limiting":true,"self_hostable":true,"multi_provider":true,"vpc_deployment":true,"otel_compatible":true,"deployment_model":"self-hosted","llm_observability":true,"prompt_management":true,"streaming_support":true,"architecture_model":"open_source_proxy","framework_agnostic":true,"experiment_tracking":true,"budget_spend_controls":true,"guardrails_moderation":"built-in","openai_compatible_api":true,"request_cost_observability":true,"mit_or_apache_permissive_oss_license":true,"organization_wide_cost_tracking_and_chargebacks":true}` | `{"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}` |
| integrations.count | 11 | 1,600 |
| integrations.list | `[{"name":"Databricks"},{"name":"AWS S3"},{"name":"Google Cloud Storage"},{"name":"Azure Storage"},{"name":"AzureML"},{"name":"Kubernetes"},{"name":"LangChain"},{"name":"Pydantic AI"},{"name":"Anthropic Claude"},{"name":"OpenAI"},{"name":"Google Gemini"},{"name":"SAP AI Core"},{"name":"JFrog"},{"name":"Aliyun"},{"name":"PostgreSQL"},{"name":"MySQL"},{"name":"MSSQL"},{"name":"Claude Code"},{"name":"OpenAI Codex"},{"name":"Gemini"},{"name":"Anthropic"},{"name":"Ollama"},{"name":"OpenClaw"},{"name":"Qwen Code"},{"name":"LiteLLM"},{"name":"Amazon S3"},{"name":"OpenTelemetry/OTLP"},{"name":"OpenAI-compatible endpoints"}]` | `[{"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}]` |
| language.primary | Python | - |
| license.spdx | Apache-2.0 | - |
| market.availability | - | `{"primaryMarkets":[],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` |
| platform.support | `{"cli":true,"web":true}` | `{"cli":true,"web":true}` |
| pricing | `{"type":"open_source","freeTier":true,"sourceUrl":"https://mlflow.org","retrievedAt":"2026-08-14T21:35:48.733Z"}` | `{"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"]}` |
| pricing.free_tier | yes | yes |
| pricing.model | open_source | freemium |
| pricing.price_level | free | mid |
| pricing.starting_price | - | `{"amount":49,"currency":"USD"}` |
| pricing.transparent | yes | yes |
| release.cadence_days | 10 | - |
| release.history | `[{"url":"https://github.com/mlflow/mlflow/releases/tag/model-catalog/latest","date":"2026-04-06T05:49:14Z","type":"stable","version":"model-catalog/latest"},{"url":"https://github.com/mlflow/mlflow/releases/tag/v3.16.0","date":"2026-09-04T08:30:54Z","type":"stable","version":"v3.16.0"},{"url":"https://github.com/mlflow/mlflow/releases/tag/v3.15.2","date":"2026-08-26T08:34:31Z","type":"stable","version":"v3.15.2"},{"url":"https://github.com/mlflow/mlflow/releases/tag/v3.15.1","date":"2026-08-03T11:09:58Z","type":"stable","version":"v3.15.1"},{"url":"https://github.com/mlflow/mlflow/releases/tag/v3.15.0","date":"2026-07-31T08:59:13Z","type":"stable","version":"v3.15.0"},{"url":"https://github.com/mlflow/mlflow/releases/tag/v3.14.0","date":"2026-06-17T08:50:33Z","type":"stable","version":"v3.14.0"},{"url":"https://github.com/mlflow/mlflow/releases/tag/v3.13.0","date":"2026-06-01T23:24:24Z","type":"stable","version":"v3.13.0"},{"url":"https://github.com/mlflow/mlflow/releases/tag/v3.13.0rc0","date":"2026-05-22T07:41:13Z","type":"prerelease","version":"v3.13.0rc0"},{"url":"https://github.com/mlflow/mlflow/releases/tag/ts/v0.2.0","date":"2026-05-15T04:09:03Z","type":"stable","version":"ts/v0.2.0"},{"url":"https://github.com/mlflow/mlflow/releases/tag/v3.12.0","date":"2026-05-05T23:48:58Z","type":"stable","version":"v3.12.0"},{"url":"https://github.com/mlflow/mlflow/releases/tag/v3.12.0rc0","date":"2026-04-28T23:25:56Z","type":"prerelease","version":"v3.12.0rc0"},{"url":"https://github.com/mlflow/mlflow/releases/tag/ts/v0.2.0-rc.1","date":"2026-04-13T09:42:04Z","type":"prerelease","version":"ts/v0.2.0-rc.1"},{"url":"https://github.com/mlflow/mlflow/releases/tag/v3.11.1","date":"2026-04-08T05:29:25Z","type":"stable","version":"v3.11.1"},{"url":"https://github.com/mlflow/mlflow/releases/tag/v3.11.0rc1","date":"2026-04-01T09:14:13Z","type":"prerelease","version":"v3.11.0rc1"},{"url":"https://github.com/mlflow/mlflow/releases/tag/v3.11.0rc0","date":"2026-03-16T14:02:42Z","type":"prerelease","version":"v3.11.0rc0"},{"url":"https://github.com/mlflow/mlflow/releases/tag/v3.10.1","date":"2026-03-05T14:47:14Z","type":"stable","version":"v3.10.1"},{"url":"https://github.com/mlflow/mlflow/releases/tag/v3.10.0","date":"2026-02-20T16:05:05Z","type":"stable","version":"v3.10.0"},{"url":"https://github.com/mlflow/mlflow/releases/tag/v3.10.0rc0","date":"2026-02-12T05:01:00Z","type":"prerelease","version":"v3.10.0rc0"},{"url":"https://github.com/mlflow/mlflow/releases/tag/v3.9.0","date":"2026-01-29T08:49:56Z","type":"stable","version":"v3.9.0"},{"url":"https://github.com/mlflow/mlflow/releases/tag/v3.9.0rc0","date":"2026-01-16T04:48:57Z","type":"prerelease","version":"v3.9.0rc0"}]` | - |
| reliability.status_page | - | yes |
| security.gdpr | - | yes |
| security.hipaa | - | yes |
| security.iso27001 | - | yes |
| security.scorecard | 5.5 | - |
| security.soc2 | - | yes |
| security.trust_center | https://mlflow.org/articles/tags/ai-compliance-policies/ | - |
| security.vulnerabilities | `{"count":82,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=mlflow&per_page=100","last_12m":29,"max_severity":"CRITICAL"}` | - |

## Capabilities (MLOps & LLMOps Tools)

| Capability | MLflow | Portkey |
|---|:--:|:--:|
| **Core** |  |  |
| Tool role | End-to-end ML platform | Model gateway / router |
| **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 2026-09-21T02:34:46.392Z. "-" = undocumented, not absent.*