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]
LLM gateways
One OpenAI-compatible API in front of many model providers, with keys, budgets, fallbacks and usage logs.
Changes in this category (RSS)
Side by side
| Tool | Stars | Licence | Terms | Self-hosted | Language | Latest | Last push |
|---|---|---|---|---|---|---|---|
| LiteLLM | 60k | Other | Open core | Yes | Python | v1.104.0 | 2026-10-06 |
| New API | 49k | AGPL-3.0 | Open source | Yes | Go | v1.0.0-rc.41 | 2026-10-06 |
| Portkey Gateway | 13k | MIT | Open source | Yes | TypeScript | v1.15.2 | 2026-05-25 |
| Bifrost | 8.6k | Apache-2.0 | Open source | Yes | Go | ent-v2.2.6-base | 2026-10-06 |
4 tools
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.
- Language
- Go
- Licence
- AGPL-3.0
- Stars
- 49k
- Latest
- v1.0.0-rc.41
- Last push
- 2026-10-06
A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
- Language
- TypeScript
- Licence
- MIT
- Stars
- 13k
- Latest
- v1.15.2
- Last push
- 2026-05-25
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
- Language
- Go
- Licence
- Apache-2.0
- Stars
- 8.6k
- Latest
- ent-v2.2.6-base
- Last push
- 2026-10-06