alternatives to
Hosted API that routes requests to hundreds of models from many providers, with one key and one bill. A closed product from OpenRouter.
| Tool | Fit | Stars | Licence | Terms | Self-hosted | Language | Latest | Last push |
|---|---|---|---|---|---|---|---|---|
| LiteLLM | Partial | 60k | Other | Open core | Yes | Python | v1.104.0 | 2026-10-06 |
| New API | Partial | 49k | AGPL-3.0 | Open source | Yes | Go | v1.0.0-rc.41 | 2026-10-06 |
| Portkey Gateway | Partial | 13k | MIT | Open source | Yes | TypeScript | v1.15.2 | 2026-05-25 |
| Bifrost | Partial | 8.6k | Apache-2.0 | Open source | Yes | Go | ent-v2.2.6-base | 2026-10-06 |
4 alternatives
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
A proxy with one OpenAI-compatible API over 100+ providers, with virtual keys, budgets and fallbacks. You bring the provider keys.
A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management.
One OpenAI-compatible API over many providers, with users, quotas and usage billing. You bring the provider keys.
A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Routing, retries and fallbacks across many providers through one API. You bring the provider keys.
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
A Go gateway with one OpenAI-compatible API over many providers, with virtual keys, budgets and failover. You bring the provider keys.