LiteLLM vs LLM Gateway
LiteLLM leads on trust: 78.1/100 (Grade B) against 63.8/100 (Grade C), a 14.3-point gap. LiteLLM leads on adoption and rests on broader evidence; LLM Gateway leads on supply-chain integrity.
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]
Choose LiteLLM if adoption matters most.
- +12.2Adoption: 62.6k GitHub stars against 1.7k
- A vs CEvidence coverage: 4 of 5 independent signal types, against 2
Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.
Choose LLM Gateway if supply-chain integrity matters most.
- +0.5Safety / Integrity: OSSF Scorecard 6.3 against 5.9
Where they differ
1 dimension identical: Identity 10.8 · Full evidence table
An independent, evidence-based trust comparison of LiteLLM and LLM Gateway, two LLM Gateways & Infra projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Full evidence
| Signal | LiteLLMBerriAI/litellm | LLM Gatewaytheopenco/llmgateway |
|---|---|---|
| HVTrust score | 78.1 | 63.8 |
| Evidence grade | B | C |
| Coverage grade | A | C |
| Overall rank | #208 | #561 |
| Rank in LLM Gateways & Infra | #4 | #7 |
| GitHub stars | 62.6k | 1.7k |
| Last updated | today | 1d ago |
| Build provenance | No | No |
| OSSF Scorecard | 5.9 / 10 | 6.3 / 10 |
| License | NOASSERTION | NOASSERTION |
| Downloads | 23.1M/wk | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 12.4 | 12.9 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 13.5 | 13.9 |
| Maintenance / 20 | 20.0 | 19.9 |
| Adoption / 20 | 20.0 | 7.8 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Declared |
| External providers | 7 — Amazon Bedrock, Anthropic, Google Gemini, … | 2 — OpenAI, Postgres |
| Requires API keys | Yes | Yes |
| Plugin surface | plugins | — |
| Provenance drift | Match | — |
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.4 →