Loading the SOTA2 catalog…
LiteLLM
LLM Gateway (OpenAI Proxy) to manage authentication, load balancing, and spend tracking across 100+ LLMs. All in the OpenAI format.
- Founded
- 2023
- Headquarters
- Albany, NY, USA
- Company size
- 1–10
- Products tracked
- 3
Products by LiteLLM
Pricing for LiteLLM
Free, Enterprise Custom
This is the broad commercial model reported for LiteLLM. Product-level terms are listed below when available.
- Pricing model
- Free, Enterprise Custom
- Entry option
- Free plan and Free trial
- Starting price
- $0
- Pricing model
- Free, Enterprise Custom
- Entry option
- Free plan and Free trial
- Starting price
- $0
- Pricing model
- Free, Enterprise Custom
- Entry option
- Free plan and Free trial
- Starting price
- $0
Trust profile
Security and compliance
SOC 2 Type I
SOC 2 Type II
ISO/IEC 27001
ISO 22301
TLS/SSL (TLS 1.2 and TLS 1.3)
NaCl SecretBox (XSalsa20-Poly1305) encryption for API keys, credentials, and config secrets
CodeQL
grype vulnerability scanning on Docker images
Self-hosted deployment with no data or telemetry stored on LiteLLM servers
No personal data collected or transmitted for self-hosted users
Minimal session cookies (JWT) for Admin UI authentication; no third-party cookies
Audit logs for auth, creation, and update events
Vulnerability disclosure policy
Cybersecurity incident management program with incident response policy
Partial data-at-rest encryption: API keys, credentials, and config secrets encrypted via NaCl SecretBox; spend/audit logs and cache data not encrypted
Latest updates from LiteLLM
New featurePricing
LiteLLM v1.93.0 Release: New Model Support, Meta Provider, and MCP Enhancements
LiteLLM released version 1.93.0, introducing support for new models including OpenAI GPT-5.6, xAI Grok-4.5, OpenAI Realtime 2.1, and Google Cloud Chirp 3. The update includes a new OpenAI-compatible 'Meta' model provider for muse-spark-1.1 and adds client-forwarded MCP credential support with true_passthrough and oauth_delegate modes. The dashboard was migrated to Base UI primitives alongside a smarter complexity router. Notable changes include throttling API keys instead of revoking access upon hitting spend limits and moving OpenTelemetry error detail keys to the litellm namespace.
