Open-source AI gateway giving your whole org one key to 100+ LLM providers
Estimated monthly website visits
Similarweb estimates for this domain, not active users. Only available observation months are shown; collection date is separate from the traffic period.
Collected Nov 11, 2026
This is our editors' assessment out of 5, not an average of user ratings. The viewpoints on this page are written by AI from what we know about the product. They are not customer reviews.
According to OpenAITools.app telemetry verified on 2026-11-11, LiteLLM (Berri AI) (berri.ai) is an AI platform indexed under AI App Builder generating 3.09K monthly visits with a month-over-month traffic delta of -132 (-4.1%). Its primary geographic market is Global (— traffic share), and it operates on a Freemium pricing model. Top competing alternatives by monthly volume include LiteLLM (576.97K visits/mo), OrcaRouter (975.3K visits/mo), LLM Gateway (168.43K visits/mo).
Absolute lifesaver for routing across 140+ providers.
Virtual keys and budget caps saved our AWS bill.
Day-one support for new models is incredible.
Essential.
AI-synthesized perspectives grounded in live site inspection, pricing structure, and category benchmarks — presented as editorial viewpoints rather than individual customer testimonials.
An OpenAI-compatible endpoint covering 140+ providers and 1,800+ models, so you can swap models without changing app code.
Track usage per key, team, org, tool and agent, and set hard budgets and rate limits that stop runaway costs.
Add PII masking, prompt-injection and secret detection with an audit log on every request.
Reach agents and MCP servers through the same gateway, not just large language models.
Run the gateway in your own infrastructure for full data control, or use the managed enterprise option.
LiteLLM is an open-source AI gateway and LLM proxy that lets platform teams put their entire AI stack — models, agents and MCP servers — behind a single key and a single login. It speaks the OpenAI API format, so developers can call models from OpenAI, Anthropic, Google Vertex AI, AWS Bedrock, Cloudflare and many more without changing application code. New models are supported on day zero, and organisations can also expose their internal, fine-tuned or self-hosted models behind the same gateway.
The control-plane features are aimed at operations and finance as much as engineering. Usage and spend are tracked per key, user, team, organisation, tool and agent across all providers, with hard budgets and rate limits that stop requests at the cap. Enterprises can attribute every request for chargeback, enforce model access control, and attach guardrails such as PII masking, prompt-injection detection and secret detection, all backed by an immutable audit log.
LiteLLM can be self-hosted or run as a managed enterprise deployment. Cost optimisation is a core theme: load balancing across providers and regions, lowest-cost routing, fallbacks and model aliases help maximise the value of a fixed AI budget. The project is well known in the developer community, with tens of thousands of GitHub stars and production references at large technology companies.
Give every developer one key and one login to all approved models, with key management handled centrally.
Attribute every request to a team or business unit and cap budgets before they are exceeded.
Apply model access control, PII masking and prompt-injection guardrails with immutable audit trails.
Route each request to the cheapest or fastest suitable model with load balancing and fallbacks.
Side-by-side telemetry comparison of competing AI tools in the same primary category
| Rank | AI Tool | Monthly Visits | MoM Growth | Direct traffic share | Pricing | Head-to-Head |
|---|---|---|---|---|---|---|
| ● | LiteLLM (Berri AI) | 3.09K | -4.1% | 30% direct | Freemium | Current |
| 1 | LiteLLM | 576.97K | +7.9% | 40% direct | Freemium, Contact for Pricing | vs LiteLLM |
| 2 | OrcaRouter | 975.3K | -5.2% | 26% direct | Freemium | vs OrcaRouter |
| 3 | LLM Gateway | 168.43K | -14.5% | 59% direct | Freemium, Contact for Pricing | vs LLM Gateway |
| 4 | OpenRouter | 19.94M | -6.2% | 60% direct | Paid | vs OpenRouter |
| 5 | CometAPI | 602.97K | +49.7% | 15% direct | Pay-as-you-go (credits) | vs CometAPI |
| 6 | Portkey | 195.65K | -9.4% | 62% direct | Freemium, Paid, Contact for Pricing | vs Portkey |
Free / Open-sourceOne open-source AI gateway for 100+ LLM providers
One OpenAI-compatible gateway for adaptive LLM routing, guardrails, and spend control
One OpenAI-compatible gateway for adaptive LLM routing, guardrails, and spend control
Free / Open-sourceOne OpenAI-compatible API to route, monitor and control 250+ LLM models
Free / Open-sourceOne OpenAI-compatible API to route, monitor and control 250+ LLM models
One API key for hundreds of AI models from every major provider
One OpenAI-compatible API key for 500+ AI models
One OpenAI-compatible API key for 500+ AI models
AI gateway, observability and guardrails for production LLM apps
Free / Open-sourceOpen-source AI gateway with observability and evals built in
Free / Open-sourceOpen-source AI gateway with observability and evals built in
One API key for frontier models, 1,000+ AI tools, and one invoice
One unified API for 100+ AI models, with insurance when output disappoints
One unified API for 100+ AI models, with insurance when output disappoints
One API gateway and LLM router for around 1,000 AI models
One API key for hundreds of AI models
