<div align="center"> <img src="./web/public/favicon.svg" alt="GPT-Load" width="96">

GPT-Load

A self-hosted AI gateway for multi-channel, multi-credential setups

API keys, subscription accounts, traffic scheduling, failure handling, request logs, and usage accounting — behind a single entry point.

English · 中文 · 日本語 | Official Website

<a href="https://trendshift.io/repositories/14880" target="_blank"><img src="https://trendshift.io/api/badge/repositories/14880" alt="tbphp/gpt-load | Trendshift" width="220" height="48"/></a> <a href="https://hellogithub.com/repository/tbphp/gpt-load" target="_blank"><img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=554dc4c46eb14092b9b0c56f1eb9021c&claim_uid=Qlh8vzrWJ0HCneG" alt="Featured｜HelloGitHub" width="220" height="47"/></a>

</div>

---

Sponsors

_{Become a sponsor}

<details open> <summary>Sponsor details (collapsible)</summary> <table> <tbody> <tr> <td width="180"><a href="https://ofox.ai/?utm_source=github&amp;utm_medium=sponsorship&amp;utm_content=gpt_load" target="_blank" rel="noopener noreferrer"><img src="./screenshot/ofoxai.svg" alt="OfoxAI" width="150"></a></td> <td><strong>OfoxAI: Text, image, and video AI in one platform</strong><br>OfoxAI is a unified AI API platform bringing together text, image, and video models from multiple providers. With OpenAI-compatible endpoints and native Anthropic and Gemini interfaces, developers can access models for AI applications, agents, and content creation through one platform. <a href="https://ofox.ai/?utm_source=github&amp;utm_medium=sponsorship&amp;utm_content=gpt_load" target="_blank" rel="noopener noreferrer">Explore OfoxAI models and APIs →</a></td> </tr> <tr> <td width="180"><a href="https://www.packyapi.ai/register?aff=ahiS" target="_blank" rel="sponsored noopener noreferrer"><picture><source media="(prefers-color-scheme: dark)" srcset="./screenshot/packycode-dark.png"><source media="(prefers-color-scheme: light)" srcset="./screenshot/packycode-light.png"><img src="./screenshot/packycode-light.png" alt="PackyCode" width="150"></picture></a></td> <td><strong>PackyCode</strong><br>Access leading AI models through PackyCode with one API endpoint and one API key. Enjoy fast, reliable access with automatic failover and dedicated high-speed routes for Codex and Claude Code. Get started with $1 in free credits, a discount on your first top-up, and savings of up to 80% on eligible routes. Pay in RMB with no currency conversion markups or extra top-up fees. <a href="https://www.packyapi.ai/register?aff=ahiS" target="_blank" rel="sponsored noopener noreferrer">Sign up through the link and start building today.</a></td> </tr> <tr> <td width="180"><a href="https://fluxionai.space/register?source=github&amp;campaign=gptload&amp;promo=GPTLOAD" target="_blank" rel="sponsored noopener noreferrer"><img src="./screenshot/fluxionai-horizontal.png" alt="Fluxion AI" width="150"></a></td> <td><strong>One entry point to connect and manage the world's leading AI models</strong><br>Fluxion AI serves individual developers, technical teams, and enterprises with a unified API for connecting to and managing leading AI models worldwide. Dynamic multi-route scheduling improves availability, while model performance, response times, and costs remain transparent and easy to review. Depending on the model and route, API calls can cost 40%–98% less than official or benchmark prices. Visit and sign up now to receive $7 in API credits. (<a href="https://fluxionai.space/register?source=github&amp;campaign=gptload&amp;promo=GPTLOAD" target="_blank" rel="sponsored noopener noreferrer">Dedicated link</a>)</td> </tr> <tr> <td width="180"><a href="https://www.axisnow.io/zh"><img src="./screenshot/axisnow.jpg" alt="AxisNow" width="150"></a></td> <td>Protect and accelerate websites and APIs, <strong>serving users in mainland China</strong> and around the world, and extend acceleration and security capabilities to native/mobile apps through a client SDK — <strong>self-built private-deployment CDN | subscription-based high-protection CDN | an independently controllable, flexibly composable CDN network.</strong></td> </tr> <tr> <td width="180"><a href="https://go.apimart.ai/gh-gpt-load"><img src="./screenshot/apimart.png" alt="APIMart" width="150"></a></td> <td>Thanks to APIMart for sponsoring this project! APIMart is a low-cost API platform for AI image &amp; video generation — GPT-Image-2 from $0.006/image, 160+ images per dollar. One async API covers both image and video: submit a task, get an ID, fetch results via polling or callback. Batch tens of thousands of images without timeouts, switch models without changing code. Pay-as-you-go with no monthly fee — <a href="https://go.apimart.ai/gh-gpt-load">sign up here</a> to get started.</td> </tr> </tbody> </table> </details>

Why GPT-Load

Your application only needs one base URL and one AccessKey. Providers, accounts, credentials, models, and routing policy are all configured in the management UI.

<img src="./screenshot/architecture-overview.svg" alt="GPT-Load unified access and upstream routing architecture" width="860">

• One gateway, native protocols — Manage official APIs, cloud platforms, model services, and compatible relays together while clients keep their OpenAI, Anthropic, or Gemini native interfaces.
• One mechanism for API keys and subscriptions — Codex, Claude, Antigravity, Grok, and API-key channels share credential management, scheduling, and health handling.
• Scheduling and failure isolation built in — Multi-credential scheduling, configurable weights, retries, cooldown, blacklisting, and session affinity reduce the impact of overloaded or failing credentials.
• Observable, self-hosted, and simple to deploy — Inspect health, routes, logs, usage, and cost estimates in an embedded UI backed by SQLite, MySQL, or PostgreSQL with local credential encryption.

Quick start

[!WARNING] If you are using 1.x, read Moving from 1.x first. 2.0 cannot open, import, or migrate 1.x data in place.

1. Start the service

Requires Docker and Docker Compose.

git clone --depth 1 https://github.com/tbphp/gpt-load.git
cd gpt-load

cp .env.example .env
docker compose up -d

Confirm the service is up:

curl --fail http://127.0.0.1:3001/health

The first start generates a management key. Read it and store it safely:

docker compose exec gpt-load sh -c 'cat /app/data/auth.key'

Open http://127.0.0.1:3001 and sign in to the console with that key.

You can also set AUTH_KEY explicitly in .env before starting. By default the service listens on the loopback address only and is not exposed to the internet.

2. Initial configuration

Initial setup takes three steps:

1. Add a channel — Choose an upstream service and add one or more API keys. For subscription channels, complete the OAuth flow or import credentials as prompted.
2. Create a group — Pick a channel, then configure available models and runtime policy.
3. Create an AccessKey — Set the groups and client protocols it may use, then give the generated AccessKey to your application.

<details> <summary>OAuth callback ports for subscription channels</summary>

The Codex, Claude, and Antigravity OAuth clients use fixed callback ports. Compose publishes them on the address configured by HOST, which defaults to 127.0.0.1; setting HOST=0.0.0.0 also publishes these callback ports on all host interfaces. Because the ports are fixed by the upstream clients, only one default Compose instance can run on a host at a time.

When working over SSH or from a remote browser, the browser's localhost may not reach GPT-Load — paste the full callback URL into the authorization dialog to finish the flow.

</details>

Screenshots

Groups — View channels, models, credential counts, traffic, and health in one place

<img src="./screenshot/groups-en-US.png" alt="GPT-Load modern groups overview" width="860">

Usage statistics — Review request trends, cache hit rate, token categories, and cost estimates

<img src="./screenshot/usage-en-US.png" alt="GPT-Load modern usage statistics" width="860">

Scope

Client protocols

| Protocol | Main entry | | ----------------------- | -------------------------------------- | | OpenAI Chat Completions | POST /v1/chat/completions | | OpenAI Responses | /v1/responses and its resource paths | | OpenAI Images | POST /v1/images/... | | OpenAI Embeddings | POST /v1/embeddings | | Rerank | POST /v1/rerank | | Anthropic Messages | POST /v1/messages | | Gemini | /v1beta/models/... |

Each channel declares exactly which protocols and capabilities it can execute. GPT-Load converts between supported capabilities, but it is not a general-purpose any-protocol, any-JSON translator.

Embeddings initially uses the native OpenAI-compatible wire only on the OpenAI, OpenRouter, and OpenAI Compatible API-key channels; subscription channels and protocol conversion are not supported. An AccessKey without a protocol filter keeps its existing “all enabled protocols” behavior and therefore gains Embeddings access after upgrade. Least-privilege deployments should configure an explicit protocol filter.

Rerank uses the independent rerank protocol through POST /v1/rerank on the OpenAI Compatible, New API, and GPT-Load API-key channels. Requests contain model, query, and a text-only documents array, with optional upstream parameters such as top_n and return_documents. Streaming, subscription channels, and protocol conversion are not supported. OpenAI Compatible takes a complete API prefix (for example, https://host/v1); New API / GPT-Load take the gateway root. The upstream must implement a compatible Rerank endpoint. AccessKeys without a protocol filter also gain Rerank access. Responses containing only non-token units such as search_units remain unpriced; these units are not treated as tokens or free requests.

Built-in channels

• Official and cloud — OpenAI, Anthropic, Gemini, xAI, Azure OpenAI, AWS Bedrock, Google Vertex AI
• Model services — DeepSeek, Moonshot AI, SiliconFlow, Zhipu AI, Alibaba, Volcengine, OpenRouter, Groq
• Subscription — Codex, Claude, Antigravity, Grok
• Custom — OpenAI Compatible (any compatible relay)

Deployment and data

Docker Compose uses application-managed SQLite by default. Data lives in the gpt-load-data named volume and includes the database, auth.key, and encryption.key.

[!IMPORTANT] encryption.key decrypts channel credentials. When backing up or migrating, the database and the key must be kept together. Once the key is lost or replaced, existing encrypted credentials cannot be recovered, and this version does not support master key rotation.

<details> <summary>Using an external database</summary>

Use the unified DATABASE_DSN to connect SQLite, MySQL, or PostgreSQL:

mysql://user:password@db.example:3306/gpt_load?charset=utf8mb4&collation=utf8mb4_bin
postgres://user:password@db.example:5432/gpt_load?sslmode=require

</details>

Common operations:

docker compose logs -f      # view logs
docker compose pu