MLRun vs TrueFoundry AI Gateway

MLRun is an open-source framework for orchestrating machine-learning and generative-AI applications across their lifecycles. It automates data preparation, model tuning, customization, validation, and optimization for ML models and large language models over elastic resources. Its feature store can collect, transform, store, catalog, serve, and monitor data features. MLRun supports multi-cloud, hybrid, and on-premises deployments with built-in observability; documented options include Kubernetes, AWS, Azure AKS, and Iguazio’s managed service. The ecosystem includes storage and data systems such as S3, Google Cloud Storage, BigQuery, Snowflake, Kafka, Spark, and Dask, alongside PyTorch, TensorFlow, XGBoost, and ONNX. CI/CD integrations include GitHub Actions, GitLab CI/CD, Jenkins, and Kubeflow Pipelines. MLRun also lists model registry, experiment tracking, pipeline orchestration, model serving, data versioning, and managed compute. The open-source plan costs nothing and includes community support. Managed MLRun includes LDAP integration, user and group management, service authentication and authorization, secured API-gateway authentication, service monitoring, log management, and 24/7 enterprise support.

TrueFoundry AI Gateway sits between applications and model providers to manage model access, routing, governance, observability, security, and cost controls. Its unified API supports chat, completion, embedding, and reranking models. TrueFoundry says the gateway connects to more than 1,000 LLMs across more than 35 platforms, including OpenAI, AWS Bedrock, Google Vertex AI, Azure OpenAI, and Anthropic. Routing options include latency-based selection, weighted load balancing, and automatic fallbacks. The service tracks token usage, latency, errors, and request volumes, and supports centrally stored request and response logs. Teams can set rate limits and cost or token quotas, with role-based access controls. MCP connections include tools such as Slack, GitHub, Confluence, and Datadog, with policies for tool calls. Deployment includes SaaS, with VPC, on-premises, and air-gapped options for Enterprise. Developer is free; Pro costs $25 a month, billed per user. Developer includes 10,000 requests per user monthly, while Pro includes 20,000 and charges $20 per additional 100,000 requests.