Agentic Index
LiteLLM vs Portkey (2026)
The two gateways most often compared, split by what sits around the routing.
LiteLLM is the open source standard: one OpenAI compatible interface to more than a hundred providers with keys, budgets and routing, free to self host, enterprise from around 250 dollars a month. Portkey wraps a similar gateway in governance, adding MCP Gateway support, audit logs and enterprise compliance, free for development and 49 dollars a month for production, documenting 8 of 14 against LiteLLM's 7. Same core job, and Portkey is the one that answers a security review.
Choose LiteLLM if
- Self hosting is the requirement and an open source gateway you fully control is the point.
- Provider breadth decides it: more than a hundred providers behind one interface.
- Your team lives in Python and wants the SDK as much as the proxy.
Choose Portkey if
- Governance is the reason for the gateway: audit logs and compliance are what you are buying.
- MCP Gateway support is part of your architecture already.
- Production pricing at 49 dollars a month beats a self hosted deployment you have to operate.
| At a glance | LiteLLM | Portkey |
|---|---|---|
| Category | Agent infrastructure | Agent infrastructure |
| Entry price | Open source, free to self host; Enterprise from about $250/mo (contact sales) | Free Dev (10K logs/mo) · Production $49/mo · open source gateway |
| Free / trial | MIT licensed open source core, free to self host | Free Dev plan (10K recorded logs/mo) |
| Pricing confidence | public partial | public exact |
| Feature | L LiteLLM |
P Portkey |
|---|---|---|
| Action & orchestration | ||
|
Integrations & Tool Calling Ability to connect agents to real systems through native integrations, OAuth-authenticated actions, custom tools, APIs, webhooks, or MCP-compatible tools. |
Full / Explicit | Full / Explicit |
|
Workflow Orchestration Ability to sequence, branch, retry, route, and combine deterministic workflow nodes with autonomous agent steps. |
No / Not documented | No / Not documented |
|
Triggers & Channel Coverage How agents wake up and where they work: schedules, webhooks, message events, CRM events, inbox events, chat, email, voice, and collaboration tools. |
No / Not documented | No / Not documented |
| Knowledge & context | ||
|
Knowledge Grounding & RAG Ability to ground agent behavior in company data through document ingestion, retrieval, external knowledge APIs, semantic search, or RAG layers. |
No / Not documented | No / Not documented |
|
Memory & State Persistence Ability to persist context across a run, conversation, workflow, user, team, or longer-term memory layer. |
No / Not documented | No / Not documented |
| Control & trust | ||
|
Human Oversight & Guardrails Approval steps, consent checkpoints, escalation rules, structured guardrails, policy constraints, and pause/resume controls. |
Partial | Full / Explicit |
|
Security, Identity & Governance RBAC, SSO, auditability, encryption, least-privilege tool access, compliance posture, and data handling policy. |
Full / Explicit | Full / Explicit |
|
Observability & Auditability Traces, logs, execution histories, metrics, audit events, and debugging detail for production agent behavior. |
Full / Explicit | Full / Explicit |
|
Deployment & Data Residency Deployment modes and options, including SaaS, dedicated cloud, VPC, on-prem, hybrid, local runtime, and self-hosting. |
Full / Explicit | Full / Explicit |
| Solution readiness | ||
|
Prebuilt Agents, Templates & Packs Ready-made workflows, packaged employees, templates, blueprints, industry solutions, and role-specific agents that reduce time-to-value. |
No / Not documented | No / Not documented |
| Platform extensibility | ||
|
Model Flexibility & Routing Ability to work across multiple foundation models, route tasks to different models, or let buyers bring their own providers and keys. |
Full / Explicit | Full / Explicit |
|
APIs, SDKs & MCP Extensibility Composability layer: stable APIs, SDKs, MCP tool consumption/serving, custom tools, and integration into internal systems. |
Full / Explicit | Full / Explicit |
|
Testing, Debugging & Optimization Testing, debugging, scoring, retries, fallbacks, quality gates, and optimization loops for improving agent workflows before and after deployment. |
Partial | Full / Explicit |
| Specialist automation | ||
|
Browser & Computer Use Browser, desktop, or remote/local computer control for workflows that cannot be handled through stable APIs alone. |
No / Not documented | No / Not documented |
Pricing snapshot
Sourced from the Index pricing dataset · open each vendor's profile for full detail.
| Pricing | L LiteLLM |
P Portkey |
|---|---|---|
|
Entry price Lowest public entry point |
Open source, free to self host; Enterprise from about $250/mo (contact sales) | Free Dev (10K logs/mo) · Production $49/mo · open source gateway |
|
Pricing confidence How public the numbers are |
Public — partial | Public — exact |
|
Billing Primary billing axis |
license and self hosted infrastructure | usage |
|
Variable cost Workload / overage exposure |
High variable cost | Medium variable cost |
|
Free tier / trial Try before you buy |
Free tier
|
Free tier
|
|
Buying motion Self-serve vs sales call |
Mixed | Mixed |