Home / Directory / AI SaaS tooling / Prompt / app frameworks / LiteLLM
LiteLLM
Open-source AI gateway and LLM proxy (from BerriAI) that puts many model providers behind one OpenAI-compatible API with spend controls, routing, and self-host options. LiteLLM had two release-pipeline security incidents in 2026: malicious PyPI versions 1.82.7 and 1.82.8 on March 24, and a compromised v1.107.0 on PyPI and Docker on October 21. The company says its private enterprise registry was not affected by the October incident.
Platform and AI engineering teams that want a self-hosted LLM gateway with budgets, routing, and one API across many providers.
Teams that only need a prompt playground or red-team eval harness, or buyers who refuse to operate any gateway themselves.
Co-founded by Krrish Dholakia.
Verdict
LiteLLM is a good fit when your real problem is governing many model providers behind one API. The open-source gateway is free to self-host; Enterprise adds SSO, audit, and support sized to request capacity, not a per-token markup. Practitioners like provider coverage and spend controls; prompt evaluation specialists like Promptfoo still complement a gateway instead of replacing it.
Score Breakdown
How LiteLLM scores in the categories that matter to its buyers.
Pricing
LiteLLM publishes an open-source self-host path at $0 and Enterprise quotes on litellm.ai/pricing. Enterprise is sized to gateway request capacity and support needs, not a per-token list. Figures below are USD signals as of September 2026.
| Plan / SKU | Meter | Price (USD) | What stands out |
|---|---|---|---|
| Open Source self-host | n/a | $0 | MIT-licensed gateway; you operate infra |
| Enterprise | annual capacity | Custom quote | SSO, SCIM, audit, SLAs, air-gap options |
| Enterprise trial | 30 days | Trial key | Instant trial path described on site |
| Marketplace / reseller | annual | Custom | AWS Marketplace and reseller routes |
The Field at a Glance
How LiteLLM compares with other Prompt / app frameworks vendors we reviewed, by Overall Score and relative typical engagement cost.
LiteLLM scores 8.0 in Prompt / app frameworks, ahead of Portkey (7.9), Helicone (7.4), and PromptLayer (6.9). Relative cost lands lower for this subcategory.
Compared with …
- LiteLLM vs Portkey 8.0/7.9
- LiteLLM vs PromptLayer 8.0/6.9
- LiteLLM vs Not Diamond 8.0/7.4
Use-case matrix
| Use case | Fit | Notes |
|---|---|---|
| Multi-provider LLM gateway | Strong | Core LiteLLM product. |
| Budgets, keys, and spend attribution | Strong | Platform-team focus. |
| Self-host / air-gapped deploy | Strong | OSS + Enterprise air-gap. |
| Prompt eval / red-teaming suite | Mixed | Promptfoo is built for prompt evaluation and red-teaming. LiteLLM is a gateway. |
| Prompt CMS / playground-only | Mixed | PromptLayer manages prompts and logs. LiteLLM routes requests. |
| Managed creative video tools | Poor | LiteLLM does not build video tools. |
Review Excerpts
Excerpts from public reviews and forum discussions of LiteLLM, plus representative buyer views drawn from public information. Paid reviews and pay-for-play sites were excluded.
“What worries me is that this seems to be the second time this happened and there's not even a notification on litellm.ai about it.”
“One OpenAI-compatible endpoint let us swap providers and track spend per team without touching application code.”
Representative buyer view
“We run the proxy in Kubernetes with virtual keys and budgets for each product team.”
Representative buyer view
Where customer reviews couldn't be found, our analysts attempted to give a voice to buyer sentiment, drawing on real information from review sites, forums, and product documentation.
Based on: LiteLLM documentation
Company Facts
- Founded
- 2023 (Y Combinator)
- Headquarters
- San Francisco (Y Combinator)
- Employees
- About 20 (Y Combinator)
- Accelerator
- Y Combinator, Winter 2023 batch (Y Combinator)
- Security incidents
- Malicious PyPI releases 1.82.7 and 1.82.8 on March 24, 2026 (LiteLLM); compromised release v1.107.0 on PyPI and Docker on October 21, 2026 (LiteLLM)
- Website
- litellm.ai
Key Leadership
Krrish Dholakia
Co-founder and CEO
Methodology
This page is an independent evaluation of LiteLLM for buyers comparing options in prompt / app frameworks. AI Industry Reviews accepts no sponsorships, advertising, or pay-for-placement fees. LiteLLM did not pay for this review.
What we scored
The headline number is an Overall Score on a 0-10 scale. Eight criteria fall under it in two groups.
- Buyer outcomes (for prompt / app frameworks)
- Multi-provider gateway coverage
- Spend control & budgets
- Self-host / air-gap readiness
- Enterprise governance extras
- Company & commercial
- Innovation & product leadership
- Project management & communication
- Pricing
- Contract fairness
Pricing measures whether the price looks fair for the value delivered, including packaging and renewal friction that show up in real buying cycles.
Score Composition
| Input | Weight | What it covers |
|---|---|---|
| Reviews | 40% | A proprietary read of what practitioners say about likes, complaints, and day-to-day use, including public review sites, forums, and private chat rooms. Paid reviews and pay-for-play sites are out of scope. |
| Product | 35% | Hands-on look at screens and workflows. |
| Pricing | 15% | Whether the price looks fair for what you get. |
| Docs & training | 10% | Docs, tutorials, and training material. |
How we balanced the evidence
The Overall Score is the simple average of the eight criteria. Recommendation language follows that score and the use-case matrix above.
Scope
LiteLLM is graded here as prompt / app frameworks. Criteria scores can move as more review volume and product checks are added.