LiteLLM vs Portkey

The question that decides it: Do you want to build and run the governance layer yourself, or pay for one that already exists?

Our verdict

Want maximum provider breadth for free and have platform engineers to run it: LiteLLM. Want RBAC, SSO, audit logs, guardrails and prompt management working this week without building them: Portkey, at $49/month for the Production tier.

Why

Both have an open-source core and both can be self-hosted, so the licence is not the dividing line people expect. LiteLLM is MIT with the whole proxy free forever, including virtual keys, team budgets, RPM/TPM limits and guardrails. Portkey is open core: an MIT-licensed gateway covering routing, fallbacks, conditional routing, semantic cache, budgets and guardrails, with a hosted control plane on top.

Coverage favours LiteLLM decisively. 140+ providers against Portkey's 40 to 48. Neither publishes a model total worth quoting - LiteLLM states none at all, and Portkey's own pages range from 250 to 2,300 - so providers are the honest measure, and on that measure nothing else in this catalog is close to LiteLLM. It also has by far the largest community here at 57,500 GitHub stars, which matters when you are debugging a proxy at 2am and need someone to have hit your problem first.

The counterweight is scale. Third-party operators report the Python proxy hitting a GIL bottleneck past roughly 300 requests per second per instance, with P99 latency blowing out to seconds and memory growth ending in OOM. An independent 2026 comparison recommends staying under 250-300 RPS per instance. That is not fatal — you shard instances — but it is real operational work, and it means LiteLLM's free licence is not the same as a free deployment.

Portkey's pitch is that the governance layer is already built. RBAC, SSO/SCIM, audit logs, budget and rate limits, PII-redaction guardrails, plus a compliance posture spanning SOC 2, HIPAA, GDPR and ISO 27001 with custom BAAs available. For LiteLLM, SSO, RBAC, audit logs and SCIM all sit behind a commercial licence whose price is not published. If you need those controls, the honest comparison is not "free versus $49" — it is "$49 versus a quote".

The catch on Portkey is its meter. Pricing is on recorded logs rather than tokens, at $9 per additional 100,000 requests past the plan allowance. High-request, small-payload workloads — agent loops especially — inflate that number fast, and it is exactly the shape of traffic that has been growing. Model it against your actual request count, not your token count.

Which one, concretely

Choose LiteLLM if

  • You need the widest provider coverage available — 140+ providers, more than anything else here
  • You want a genuinely free, MIT-licensed proxy with no usage fee
  • You have platform engineers who can shard and operate it
  • You want batch API support, which Portkey does not list

Choose Portkey if

  • You need RBAC, SSO, audit logs and guardrails without building or negotiating for them
  • You want a documented SOC 2, HIPAA, GDPR and ISO 27001 posture from the vendor
  • Your request volume would push LiteLLM past its reported per-instance ceiling
  • You want prompt management and a semantic cache in the same control plane

What catches people out

Side by side

4 of 20 fields differ, marked with a dot. Every figure links to the vendor page it came from. Blank values read Not published rather than No — silence from a vendor is not a negative answer.

Field LiteLLM Portkey
Ease of leaving Derived score, higher is easier 100/100 Easy to leave 100/100 Easy to leave
What kind of product Category Open source Managed gateway
Who runs it Deployment model Self-host only Managed or self-host
Licence Licence MIT Open core
Models available Models available Not published 250–2,300
Model providers reachable Upstream providers Not published 40–48
Markup on model prices Token markup None Not published
Fee to add funds Credit purchase fee None Not published
Monthly cost per person Seat fee None Not published
GitHub stars GitHub stars 57,500 12,848
Delay it adds Proxy overhead 0.66 ms Not published
Requests per second ceiling Throughput 2,800 rps Not published
Similar-question caching Semantic cache Yes Yes
Content guardrails Content guardrails Yes Yes
Prompt versioning Prompt management Not published Yes
Separate keys per team or app Virtual keys Yes Not published
Spending limits Budget controls Yes Yes
MCP support MCP support Yes Yes
SOC 2 audited SOC 2 audited Not published Yes
Will sign a HIPAA agreement HIPAA BAA Not published Yes
Runs fully disconnected Air-gapped deployment Yes Not published

Verified 3 days ago for LiteLLM and Verified 3 days ago for Portkey. Want more fields, or a third option in the mix? Open these two in the full comparison tool.

Common questions

Is LiteLLM really free?

The proxy is MIT-licensed and free forever, including virtual keys, budgets, rate limits and guardrails. But SSO, RBAC, audit logs and SCIM require a commercial licence whose price is not published, and you carry the infrastructure and operational cost of running it yourself.

How much traffic can LiteLLM handle?

Third-party operators report the Python proxy hitting a GIL bottleneck past roughly 300 requests per second per instance, with P99 latency degrading to seconds. An independent 2026 comparison recommends staying under 250-300 RPS per instance and scaling horizontally beyond that.

What does Portkey actually cost?

There is a free Developer tier with 10,000 recorded logs per month, and a Production tier at $49/month. Pricing meters recorded logs rather than tokens, with $9 per additional 100,000 requests, so high-request workloads cost more than the headline suggests.