new-api vs MLflow
Two of the top projects in Gateways and observability, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
new-api
Gateway that unifies LLM providers behind OpenAI, Anthropic and Gemini APIs
MLflow
Tracing, evals, prompt registry and AI gateway plus classic ML tracking
Verdict
new-api ranks higher, 90 to 89. Of the 4 score parts we measure for both, new-api leads on 1, MLflow on 2 and 1 is even.
- Adoptionnew-api leads by 11 points, 92 to 81.
- FreshnessEven at 100.
- MaintenanceMLflow leads by 2 points, 88 to 86: close to even.
- Agent-readyMLflow leads by 15 points, 85 to 70: a wide gap.
Pick new-api if you are
Teams and operators sharing and metering access to multiple LLM providers
- Converts between OpenAI, Anthropic Messages and Gemini request formats via RelayKit
- Channel priorities, weights, retries and multiple upstream keys per channel
Pick MLflow if you are
Teams wanting one platform for GenAI tracing and ML tracking
- One-line autolog for 60+ frameworks in Python, TypeScript and Java; MCP and OTel native
- Starts with uvx mlflow server; no separate database needed to begin
| What we compare | new-api | MLflow |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 92, widely used | 81, widely used |
| Freshness | 100, active | 100, active |
| Maintenance | 86, healthy | 88, healthy |
| Agent-ready | 70, partly | 85, ready |
| Facts from GitHub and the README | ||
| Stars | 51.1k | 28.6k |
| License | AGPL-3.0 (copyleft) | Apache-2.0 (permissive) |
| Last commit | Nov 2026 | Nov 2026 |
| Last release | Oct 2026 | Oct 2026 |
| Language | Go | Python |
| Docker | Yes | Yes |
| GPU | Not needed | Not needed |
| arm64 or Apple Silicon | Mentioned | Not stated |
new-api
New API is a Go and Gin gateway that connects upstream providers such as OpenAI, Anthropic, Gemini, Azure OpenAI, AWS Bedrock, Vertex AI, DeepSeek and Qwen. It exposes them through OpenAI Chat/Responses, Anthropic Messages and Gemini endpoints. A web console handles channel routing, users, quotas, pricing and usage logs. It runs on SQLite by default, or on MySQL or PostgreSQL with optional Redis.
Who it is for: Teams and operators sharing and metering access to multiple LLM providers
Strengths
- Converts between OpenAI, Anthropic Messages and Gemini request formats via RelayKit
- Channel priorities, weights, retries and multiple upstream keys per channel
- Per-user quotas, subscriptions, usage logs and expression-based pricing
- Starts on SQLite with one container; Compose file adds PostgreSQL and Redis
Weaknesses
- AGPL-3.0 with extra terms requiring attribution and a visible project link in modified UIs
- Protocol conversion is not exact; tools and fields may not map across protocols
- Multi-node setups need shared database, secrets and Redis, or rate limits count per node
- Public or resale use brings filing and compliance duties the README leaves to the operator
- no GPU
- Docker + Compose
- Needs SQLite, MySQL >= 5.7.8 or PostgreSQL >= 9.6, Redis (optional), ClickHouse (optional, log database)
- Models: OpenAI, Anthropic, Google Gemini, Azure OpenAI, AWS Bedrock
- port 3000
MLflow
Single mlflow server (port 5000) that records OpenTelemetry traces from 60+ frameworks via one-line autolog, runs evaluations with 50+ metrics and LLM judges, versions and optimizes prompts, and fronts providers through an OpenAI-compatible AI Gateway with rate limits, fallbacks and traffic splitting. Keeps the original experiment tracking, model registry and deployment tooling. For teams wanting one platform for GenAI and ML.
Who it is for: Teams wanting one platform for GenAI tracing and ML tracking
Strengths
- One-line autolog for 60+ frameworks in Python, TypeScript and Java; MCP and OTel native
- Starts with uvx mlflow server; no separate database needed to begin
- AI Gateway adds credential management, guardrails and A/B traffic splitting
- Setup wizard lets Claude Code, Codex or OpenCode add tracing to a project
Weaknesses
- README covers the quickstart; production backend store and auth setup live in docs
- Broad scope (ML tracking plus GenAI) means a large install and UI surface
- No Dockerfile or compose file at the repo root
- TypeScript and Java coverage is smaller than Python (5 TS and 2 Java frameworks listed)
- no GPU
- Docker + Compose
- Models: any LLM provider via autolog or the AI Gateway
- port 5000
More in Gateways and observability
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.