
LiteLLM
situationalOpen-source OpenAI-compatible gateway — 100+ providers, spend keys, optional Enterprise license.
Visit litellm.ai →> **LiteLLM** — situational > Verified 2026-08-19 > Limitation: docs.litellm.ai/docs/pricing 404s; Enterprise dollars are not on a public SKU page. > > https://noemium.com/tools/litellm/Add to kitOpen in NoemiumFact-check this catalog entry for LiteLLM (dev-infra). Verdict: situational Verdict text: The self-host cousin of OpenRouter: one OpenAI-shaped interface, virtual keys, budgets, fallbacks. OSS already does a lot. Enterprise is SSO/SCIM, audit, multi-region, and a license key — docs say pricing is usage-based and sales-quoted, so this card will not copy third-party $250/$30k blogs. You still pay every upstream model bill. Limitations: - docs.litellm.ai/docs/pricing 404s; Enterprise dollars are not on a public SKU page. - SSO beyond 5 users requires the commercial license. - You run Postgres/Redis/the proxy; the "free" gateway is not zero-ops. - Several built-in guardrail callbacks are Enterprise-gated, not OSS. Receipts: https://docs.litellm.ai/docs/enterprise https://github.com/BerriAI/litellm Last verified: 2026-08-19 Find outdated prices, wrong claims, or missing limitations. Cite primary sources (docs, pricing pages, benchmarks, model cards). Do not use marketing pages.[](https://noemium.com/tools/litellm/)
ledger entry · observed by @whysanesanders
The self-host cousin of OpenRouter: one OpenAI-shaped interface, virtual keys, budgets, fallbacks. OSS already does a lot. Enterprise is SSO/SCIM, audit, multi-region, and a license key — docs say pricing is usage-based and sales-quoted, so this card will not copy third-party $250/$30k blogs. You still pay every upstream model bill.
Strengths
- One OpenAI-shaped interface to more than a hundred providers.
- Virtual keys, budgets and fallbacks in the OSS gateway.
- Self-hostable proxy and SDK without a seat license.
Known limitations
- docs.litellm.ai/docs/pricing 404s; Enterprise dollars are not on a public SKU page.
- SSO beyond 5 users requires the commercial license.
- You run Postgres/Redis/the proxy; the "free" gateway is not zero-ops.
- Several built-in guardrail callbacks are Enterprise-gated, not OSS.
Use it when
- Teams routing multiple model providers through one API shape.
- Self-hosted deployments that need spend controls and virtual keys.
- Evaluation setups that want to swap providers without code changes.
Skip it when
- You need a public, fixed Enterprise price list.
- You want a zero-ops managed service without running Postgres/Redis.
- SSO beyond five users is required without the commercial license.
Buy-check
- ·Price — freemium, OSS proxy/SDK free (self-host); SSO free up to 5 users; Enterprise license is usage-quoted (30-day trial, no public $ table); 24/7 SLA extra as of 2026-08-19. Open the pricing page, not a screenshot.
- ·Free tier — Free tier exists — burn it first.
- ·Cancel fallout — What happens to your data/projects on cancel — check the ToS, not the FAQ.
- ·Seat math — Per-seat pricing multiplies quietly. Count seats before the annual plan.
- ·Who skips it — Also skipped when: You need a public, fixed Enterprise price list.; You want a zero-ops managed service without running Postgres/Redis..
Price trailchangelog →
No price move in this repo yet.
Facts
- pricing
- freemium1
- price note
- OSS proxy/SDK free (self-host); SSO free up to 5 users; Enterprise license is usage-quoted (30-day trial, no public $ table); 24/7 SLA extra
- free tier
- yes
- open source
- yes
- api
- yes
- self-host
- yes
- category
- dev-infra
- evidence
- source-verified
- Models
- BYOK
Data: trains on inputs unknown · local processing yes
Sources
No source, no number.
Similar joball alternatives →
| tool | verdict | price | oss | self-host |
|---|---|---|---|---|
| LiteLLM | situational | freemium | yes | yes |
| Modal | ship | freemium | no | no |
| OpenRouter | ship | freemium | no | no |
| Replicate | ship | paid | no | no |
Facts from the catalog files — not scores you can buy. Quality and speed stay in the briefing, not in a fake 1–5 grid.
Modal
Serverless GPU and compute platform for running ML and AI workloads.
APIFREE TIER
freemiumfree tier ($30/mo compute); pay-as-you-go beyond
OpenRouteranchor
One API for every major model — unified billing, fallbacks and routing.
APIFREE TIER
freemiumpay-per-token pass-through plus a small fee
Replicate
Run any community model via API — pay per second, no GPU wrangling.
API
paidpay per run; image models from ~$0.003/image