Provides a massive hosted model catalog with instant access, but requires trusting a third-party platform instead of self-hosting.
#1LiteLLM records 576,967 monthly visits with +7.9% month-over-month growth and Freemium, Contact for Pricing pricing. Rivet.dev records 21,359 monthly visits with -44.3% growth and Freemium, Contact for Pricing pricing.

Run and scale durable AI agents on your own infrastructure
| Dimension / Metric | ![]() | ![]() |
|---|---|---|
| Official Domain | litellm.ai | rivet.dev |
| Pricing Model | Freemium, Contact for Pricing | Freemium, Contact for Pricing |
| Monthly Visits | 576.97K (576,967) | 21.36K (21,359) |
| MoM Traffic Delta |
| +42.48K (+7.9%) |
| -16.97K (-44.3%) |
| Primary Market & Share | 🇺🇸 United States (27.9%) | 🇺🇸 United States (39.4%) |
|---|
| Direct Visits / mo | 228.97K | 10.71K |
|---|
| User Rating | 4.8 | 4.5 |
|---|
| Supported Platforms | Website | Website |
|---|

One open-source AI gateway for 100+ LLM providers
Call 100+ providers and 1,800+ models using one request format, so you can swap models without changing application code.
Issue scoped keys per team, project or app, set monthly spend caps and see exactly who is driving usage and cost.
Distribute traffic across deployments, retry on failure and automatically fall back to another model or provider when one goes down.
Dashboards for request volume, tokens and cost per model, with support for logging and analytics integrations.

Run and scale durable AI agents on your own infrastructure
Every Actor gets a SQLite database and a filesystem, so an agent's memory and progress survive restarts and idle periods without a separate database.
Run untrusted or AI-generated code on your own infrastructure with fine-grained control over network access, filesystem permissions, and resource limits.
A node failure reschedules its Actors elsewhere with state intact, and multi-step work replays after a crash — with no checkpointing harness to build yourself.
Address an Actor directly over HTTP or hold a live WebSocket, and use the React SDK to subscribe components to an Actor's state in real time.
Provides a massive hosted model catalog with instant access, but requires trusting a third-party platform instead of self-hosting.
#1
SpecialistHosts high-performance open-weight models directly on dedicated serverless infrastructure, but does not route across external providers.
#2Delivers automated model failover and budget governance through an API gateway, but with less open-source customization.

Unified LLM gateway with failover and analytics, but offers less robust open-source developer SDK support.

Free / Open-sourceThe TypeScript framework for building, deploying, and observing AI agents

Offers advanced enterprise observability and guardrail tools, but lacks LiteLLM's lightweight self-hosted proxy simplicity.
The low-cost cloud sandbox where AI agents actually live

Provides managed multi-provider AI routing and cost tracking, but lacks the native open-source flexibility of LiteLLM.
Free / Open-sourceAn open-source alternative for unifying LLM providers, but features a less extensive ecosystem of middleware integrations.

Self-hosted cloud development environments and AI coding agents for enterprise teams

Free / Open-sourceOpen-source request routing with built-in evaluations, but has a smaller community and fewer pre-built provider connectors.

Persistent Ubuntu cloud VMs built for AI agent factories
Provides a massive hosted model catalog with instant access, but requires trusting a third-party platform instead of self-hosting.
SpecialistHosts high-performance open-weight models directly on dedicated serverless infrastructure, but does not route across external providers.
Delivers automated model failover and budget governance through an API gateway, but with less open-source customization.
Unified LLM gateway with failover and analytics, but offers less robust open-source developer SDK support.
Offers advanced enterprise observability and guardrail tools, but lacks LiteLLM's lightweight self-hosted proxy simplicity.
The low-cost cloud sandbox where AI agents actually live
Free / Open-sourceAn open-source alternative for unifying LLM providers, but features a less extensive ecosystem of middleware integrations.
Free / Open-sourceOpen-source request routing with built-in evaluations, but has a smaller community and fewer pre-built provider connectors.