LiteLLM vs Portkey
No clear leader: LiteLLM (81.0) and Portkey (78.9) are within the 5-point margin; treat as a tie. The attribute-by-attribute breakdown below, with a source and date on every value, is the honest way to compare them.
Capabilities
Feature-by-feature on the axes that matter for llm gateways. “-” means undocumented, not absent.
What each one is
The product in its own terms, so the numbers below have context.
LiteLLM
An open-source AI gateway that provides a centralized control point for managing multiple large language models from different providers. It offers virtual key management, spend tracking, budget controls, and intelligent request routing without charging per token.
Portkey
A unified platform combining an AI gateway, observability dashboards, prompt versioning, governance controls, and guardrails. Enables teams to route requests across LLM providers, monitor costs and performance, securely manage API keys, and deploy production-ready prompts with version control.
Pricing
List pricing as published by each vendor, with the date we read it. Always verify at the source before you buy.
LiteLLM
Free open-source tier. Enterprise pricing based on annual request volume, not per-token.
- Open SourceFree
- 100+ LLM providers
- Virtual keys, users & teams
- Spend tracking
- Prometheus metrics
- Logging and alerting
- +3 more
- EnterpriseContact sales
- Everything in Open Source, plus:
- SSO + SCIM provisioning
- OIDC / JWT authentication
- Audit logs on every request
- Secret manager integration
- +7 more
Portkey
Free tier with 10k logs/month. Production at $49/month with usage overages. Enterprise custom pricing for compliance-focused organizations.
- DeveloperFree
- Universal API & Key Management
- Routing, Fallbacks, Load Balancing, Retries
- 3 Prompt Templates with Playground, Versioning, Variables
- Logs, Traces, Feedback, Custom Metadata, Filters
- Simple Caching
- +3 more
- Production$49/month + $9 per 100k request overage
- 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
- +3 more
- EnterpriseContact sales
- 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
- +3 more
Platform & deployment
Where each product runs and how it can be hosted. A dash means undocumented, not unsupported.
Integrations
What each product connects to. Counts come from the vendor's own integration directory where one exists.
- OpenAI
- Anthropic
- Azure
- VertexAI
LiteLLM
- AWS Bedrock
- Cloudflare
- Google VertexAI
- Meta Llama
- Mistral AI
- NLP Cloud
- OVHCloud
- vLLM
- Nvidia NIM
- Slack
- Discord
- Microsoft Teams
- PagerDuty
- Prometheus
- AWS Secrets Manager
- Google Cloud Secret Manager
- MCP servers
- Gemini
- Bedrock
- Langfuse
- Langsmith
- Datadog
- Webhook
- +4 more
Portkey
- Google Cloud (Vertex AI, Gemini)
- AWS
- GCP
- Langgraph
- CrewAI
- Strands Agents
- Google ADK
- Claude
- Mistral
- MongoDB
Comparison generated from independently-sourced facts. Every value links to its source and retrieval date. See the method.