New API

What is New API?

New API is a self-hosted gateway that connects upstream model services (OpenAI, Anthropic, Gemini, Azure OpenAI, Bedrock, Vertex AI, DeepSeek, Qwen and other compatible APIs) and exposes them through OpenAI, Anthropic and Gemini-style endpoints. A web console manages channels, model mappings, priorities and retries, users and groups, per-key quotas, usage and audit logs, and pricing. It is a Go service that runs on SQLite for a trial or PostgreSQL/MySQL plus Redis in production.

Where it fits in a 10–200 person business

• Give every team and tool one internal API key per person while the company holds the real provider keys
• Track and cap AI spend per user, group or project across several model providers
• Switch or load-balance providers without reconfiguring each client app

These use cases are our editorial suggestions, not claims made by the project.

Can a business use New API? (license)

This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.

Data & compliance: does New API phone home?

Checked against the project's own docs and repository on Oct 30, 2026. "Not documented" means we could not find the answer in official sources; it does not mean the feature is missing or that no data is sent. Third-party services you connect (model APIs, vector databases, search engines) have their own data policies. Compare all apps.

What hardware does New API need?

The project does not publish a minimum CPU/RAM figure, so we leave the official value blank rather than guess.

GPU: No. It forwards requests to model APIs you configure.

No official CPU, RAM or disk figure is published. The documented requirements are Docker, port 3000, and a database (SQLite, MySQL 5.7.8+ or PostgreSQL 9.6+), with Redis optional.

Source: github.com/QuantumNous/new-api#quick-start

How much does it cost to host New API per month?

How to deploy New API

Method: Docker (single container, SQLite)

mkdir -p data
docker run --name new-api -d --restart unless-stopped \
  -p 127.0.0.1:3000:3000 \
  -e TZ=Asia/Shanghai \
  -v "$(pwd)/data:/data" \
  calciumion/new-api:latest
# Open http://localhost:3000 and finish the setup wizard to create the admin account

From the official instructions: github.com/QuantumNous/new-api#quick-start. Always check the source for the current version before you run it.

Known gotchas when self-hosting New API

• The repository's docker-compose.yml ships example database and Redis passwords (123456). Replace them in both the services and the connection strings, and set a persistent random SESSION_SECRET before starting. source
• Multi-node deployments must share the main database and the same SESSION_SECRET / CRYPTO_SECRET; separate Redis instances or in-memory rate limiters count limits per node. source
• The latest tag follows published builds and can change; pin a release version, read its upgrade notes and back up the database before upgrading. source
• Reselling API access or running it as a public AI service brings your own filing, licensing, content-safety and upstream-authorization obligations; the project is meant for authorized internal gateways. source

Alternatives in LLM gateway & observability

• LiteLLM AI gateway that puts 100+ LLM providers behind one OpenAI-compatible API with keys and budgets.
• Langfuse LLM observability with tracing, prompt management, evaluations and cost tracking.
• Opik Open-source LLM observability and evaluation platform for tracing, evals, prompt management and monitoring.
• Phoenix Free self-hosted LLM tracing, evaluation, datasets and prompt management from Arize.

Sources

• GitHub repository: github.com/QuantumNous/new-api
• Official documentation: docs.newapi.ai/en/docs/installation
• License text: github.com/QuantumNous/new-api/blob/main/LICENSE
• Hardware requirements, Deploy instructions: github.com/QuantumNous/new-api#quick-start
• Gotcha 1: github.com/QuantumNous/new-api/blob/main/docker-compose.yml
• Gotcha 2, Gotcha 3, Gotcha 4: github.com/QuantumNous/new-api#readme
• Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
• GitHub stars, commits and releases: GitHub REST API, fetched Oct 30, 2026