One API key for hundreds of AI models from every major provider
Manifest: Open-source gateway focused on automatic request repair and fallback, but significantly less mature than LiteLLM. LiteLLM records 576,967 monthly visits with +7.9% month-over-month growth and Freemium, Contact for Pricing pricing. Manifest records 54,135 monthly visits with -23% growth and Free pricing.

The open-source LLM gateway that fixes your agents' requests on the fly
| Dimension / Metric | ![]() | ![]() |
|---|---|---|
| Official Domain | litellm.ai | manifest.build |
| Pricing Model | Freemium, Contact for Pricing | Free |
| Monthly Visits | 576.97K (576,967) | 54.14K (54,135) |
| MoM Traffic Delta | +42.48K (+7.9%) | -16.19K (-23%) |
| Primary Market & Share | 🇺🇸 United States (27.9%) | 🇺🇸 United States (15.5%) |
| Direct Visits / mo | 228.97K | 34.26K |
| 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.

The open-source LLM gateway that fixes your agents' requests on the fly
One OpenAI-compatible endpoint reaches every configured model, provider, subscription plan or local server.
Broken or non-conforming LLM requests are repaired automatically before the error reaches your agent or app.
Automatic retry on another provider when one goes down keeps agents and workflows running.
Track every request, token and dollar broken down by agent, key and provider, with full request and response body logs.
One API key for hundreds of AI models from every major provider

Ultra-fast AI inference on the LPU and LPX platform

SpecialistHosts high-performance open-weight models directly on dedicated serverless infrastructure, but does not route across external providers.
SpecialistHosts high-performance open-weight models directly on dedicated serverless infrastructure, but does not route across external 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

One unified API for 100+ AI models, with insurance when output disappoints
One unified API for 100+ AI models, with insurance when output disappoints
AI gateway, observability and guardrails for production LLM apps

Provides managed multi-provider AI routing and cost tracking, but lacks the native open-source flexibility of LiteLLM.
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

Free / Open-sourceOpen-source AI gateway with observability and evals built in
Free / Open-sourceOpen-source AI gateway with observability and evals built in
Free / Open-sourceOpen-source LLM observability and AI gateway for shipping reliable AI apps
Free / Open-sourceOpen-source LLM observability and AI gateway for shipping reliable AI apps

Free / Open-sourceOpen-source AI gateway and developer portal for APIs and LLMs

Intelligent model routing for coding agents
Intelligent model routing for coding agents