Skip to content

LiteLLM

Independent gateway · no token markup · BYOK 0% · hosted or self-host · open source · checked Sep 23, 2026

What it costs on real workloads

ModelThrough LiteLLM
Claude Sonnet 5$400.00vs $400.00 direct
GPT-6 Sol$400.00vs $400.00 direct
Gemini 3.8 Flash$150.00vs $150.00 direct
DeepSeek V4.1 Flash$27.00vs $27.00 direct

100M input and 20M output tokens a month, paying with gateway credits.

About LiteLLM

Open source Python SDK and proxy server that calls 100+ LLM providers in the OpenAI format, with an enterprise tier for SSO, audit logs and support.

Fee on tokens
None
Pricing model
Open source, self-hosted with your own keys; enterprise license by quote
Bring your own key
0% fee
Entry plan
Enterprise
Hosting
Hosted or self-host
License
MIT (enterprise features under LiteLLM Commercial License)

Features stated: Fallbacks, Load balancing, Caching, Guardrails, Observability, Rate limits, Budgets, Prompts, OpenAI-compatible, Bring your own key. Not stated: Data residency, Private networking.

The terms, in their words

Markup
Self-hosted proxy calls providers with your own keys; no token markup stated. Hosted proxy offered via enterprise.
Free tier
Open source gateway free to self-host
Providers
100+ LLM providers
  • Deploy the open-source gateway in an afternoon
  • Virtual keys with per-key/team/user budgets
  • Drop-in replacement for any OpenAI-compatible client

Source: www.litellm.ai/enterprise

LiteLLM vsHeliconeKong AI GatewayVercel AI GatewayCloudflare AI GatewayRequestyEden AI

Sources: each gateway's own pricing page and docs, read by hand and fetched again every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Price changes by email

Thursdays, only in weeks when an LLM API list price changed.

Double opt-in. Unsubscribe any time.