# Half Off Dev

> Claude, GPT and Gemini at half the official list price, through their native Anthropic, OpenAI and Gemini APIs at https://halfoff.dev. One prepaid key. Every docs page below is plain Markdown.

## Get started

- [Overview](https://halfoff.dev/docs/index.md): Call Claude, GPT and Gemini through their native APIs at half the official list price. Swap the base URL and key; your code stays the same.
- [Quickstart](https://halfoff.dev/docs/quickstart.md): Get a key, send a GPT, Claude or Gemini request at half the official price with your existing SDK, stream it, and see what it cost.
- [Authentication](https://halfoff.dev/docs/authentication.md): How Half Off Dev API keys work: the four places a key can travel, a free way to test one, the 401 errors you may see, and how to keep keys safe.
- [Use with your tools](https://halfoff.dev/docs/integrations.md): Run Claude Code, Codex CLI, Gemini CLI, Cherry Studio, DeepChat, AionUI or any OpenAI-compatible app on half-price models with one Half Off Dev key.

## Integrations

- [Claude Code](https://halfoff.dev/docs/integrations/claude-code.md): Run Claude Code on Half Off Dev at half the official Claude price: two environment variables or settings.json, model choice, and prompt caching.
- [Codex CLI](https://halfoff.dev/docs/integrations/codex-cli.md): Run Codex CLI on GPT models at half the official price: add Half Off Dev as a model provider in config.toml, set the key, and pick a model.
- [Gemini CLI](https://halfoff.dev/docs/integrations/gemini-cli.md): Run Gemini CLI on Half Off Dev at half the official Gemini price with two environment variables, then choose a Gemini model.
- [Cherry Studio](https://halfoff.dev/docs/integrations/cherry-studio.md): Add Half Off Dev to Cherry Studio as an OpenAI-compatible provider and chat with Claude, GPT and Gemini at half the official price.
- [DeepChat](https://halfoff.dev/docs/integrations/deepchat.md): Connect DeepChat to Half Off Dev with one OpenAI-compatible provider and use Claude, GPT and Gemini models at 50% of the official price.
- [AionUI](https://halfoff.dev/docs/integrations/aionui.md): Set up Half Off Dev in AionUI as an OpenAI-compatible provider, in one click or by hand, and chat with Claude, GPT and Gemini at half price.
- [OpenAI-compatible apps](https://halfoff.dev/docs/integrations/openai-compatible.md): Any app, framework or library with a custom OpenAI endpoint can call Claude, GPT and Gemini through Half Off Dev at half the official price.
- [SDKs](https://halfoff.dev/docs/integrations/sdks.md): Use the official OpenAI, Anthropic and Google Gen AI SDKs with Half Off Dev at half the official price by setting two client options.

## Models API

- [How the gateway works](https://halfoff.dev/docs/models.md): One host serves the Anthropic, OpenAI and Gemini APIs natively. Endpoints, base URLs, accepted model ids, auth headers and what Half Off Dev touches.
- [Anthropic Messages](https://halfoff.dev/docs/models/anthropic.md): Run Claude at half price with your existing Anthropic SDK code. Swap the base URL; streaming, thinking, tool use, caching and token counts work unchanged.
- [OpenAI Chat Completions](https://halfoff.dev/docs/models/openai.md): Use the OpenAI SDK you already have to call GPT, Claude and Gemini at half price. Streaming usage, function calling, reasoning and the Responses API.
- [Gemini](https://halfoff.dev/docs/models/gemini.md): Call Gemini at half price through its native API with the Google Gen AI SDK or Gemini CLI: generateContent, SSE streaming, thinking and countTokens.
- [Models & pricing](https://halfoff.dev/docs/models/pricing.md): Every model costs half its list price per token: input, output, cache reads and cache writes. See how each call's charge is computed and list models.
- [Channel groups](https://halfoff.dev/docs/models/channel-groups.md): Claude · Value, GPT · Value and Gemini · Value pool capacity for each model family at half the list price. How to pick one per key or per request.
- [Prompt caching](https://halfoff.dev/docs/models/caching.md): Cut input costs further on top of half price: use each vendor's prompt caching, and let Half Off Dev route every conversation back to the channel holding its cache.
- [Streaming](https://halfoff.dev/docs/models/streaming.md): Stream Claude, GPT and Gemini output in each vendor's native SSE format. How early failures are hidden, how stalls surface, and what a cancelled stream costs.
- [Rate limits & failover](https://halfoff.dev/docs/models/rate-limits.md): Per-key request and concurrency limits, short capacity queues and automatic failover across channels. Status codes to expect and how to retry safely.

## Account

- [API keys](https://halfoff.dev/docs/account/api-keys.md): Issue a separate Half Off Dev key for every app, cap its spend, rate and models, and rotate or revoke it without breaking production.
- [Credits & billing](https://halfoff.dev/docs/account/billing.md): Prepaid USD balance, PayPal top-ups, voucher codes and how Half Off Dev charges each model request at half the official per-token price.
- [Usage & logs](https://halfoff.dev/docs/account/usage.md): See what each Half Off Dev key spends, read per-request tokens, latency and errors, trace calls by request id, and reconcile your balance.
- [Account security](https://halfoff.dev/docs/account/security.md): Lock down your Half Off Dev dashboard with two-factor sign-in, recovery codes and session control, and see exactly what data is stored.

## API reference

- [Introduction](https://halfoff.dev/docs/api.md): Base URLs, auth headers, response headers, rate limits and retry rules for calling Claude, GPT and Gemini through Half Off Dev's native APIs.
- [Models endpoints](https://halfoff.dev/docs/api/models.md): Request and response reference for Messages, Chat Completions, Responses, Gemini and model listing on Half Off Dev, with the headers each accepts.
- [Errors](https://halfoff.dev/docs/api/errors.md): HTTP status codes from Half Off Dev, error bodies in Anthropic, OpenAI and Gemini format, stream errors, and retry code you can paste.