Быстрый старт
The API is OpenAI-compatible. Configure your client with an API key, the base URL https://api.unquant.io/v1 and a model ID.
1. Activate your account
Accept your invitation and activate your subscription. Keys are managed under API keys in your workspace.
2. Create an API key
The full key is shown once, at creation. Store it server-side; keys in client-side code or public repositories are exposed.
3. Send a request
curl https://api.unquant.io/v1/chat/completions \
-H "Authorization: Bearer $UNQUANT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"glm-5.3-flash",
"messages":[{"role":"user","content":"Hello!"}]}'Connection settings
Your workspace shows the model ID for your plan. Any client with a custom OpenAI-compatible endpoint works.
Client guides
- How to use Claude Code with an uncensored, unlimited modelRun Claude Code on GLM-5.3-Flash or Qwen 3.8 Flash Next through Unquant's Anthropic-compatible endpoint: two environment variables, no proxy, unlimited tokens and 262K context.
- How to use OpenAI Codex CLI with UnquantAdd Unquant to OpenAI Codex CLI as a custom model provider in ~/.codex/config.toml. Unquant serves the Responses API Codex needs, so it connects directly, with unlimited tokens.
- How to add Unquant to OpenCodeAdd Unquant to OpenCode as an OpenAI-compatible provider in opencode.json and run the terminal coding agent on GLM-5.3-Flash with 262K context and unlimited tokens.
- How to use the Pi coding agent with UnquantAdd Unquant to the Pi coding agent in ~/.pi/agent/models.json as an OpenAI-completions provider and run it on GLM-5.3-Flash or Qwen 3.8 Flash Next.
- How to use Reasonix with UnquantRun Reasonix, the DeepSeek terminal coding agent, on Unquant: one provider entry in ~/.reasonix/config.toml and your key in ~/.reasonix/.env.
- How to use Hermes Agent with UnquantPoint Nous Research's Hermes Agent at Unquant as a custom OpenAI-compatible endpoint, with hermes model or ~/.hermes/config.yaml.
- Use Unquant in VS Code: Copilot Chat, Cline, Roo Code, Kilo Code and ContinueConnect VS Code to Unquant: GitHub Copilot Chat bring-your-own-key, and the Cline, Roo Code, Kilo Code and Continue extensions, each with its OpenAI-compatible settings.
- How to use Unquant in CursorPoint Cursor's chat at Unquant with your own key and base URL, and what Cursor's limits mean: a paid Cursor plan is required and only the chat panel uses your model.
- Use Unquant with Crush, Goose, Zed and AiderExact OpenAI-compatible settings to run Crush, Goose, the Zed editor and Aider on Unquant's uncensored GLM-5.3-Flash and Qwen 3.8 Flash Next.
- How to connect SillyTavern to an unlimited, uncensored APIConnect SillyTavern to Unquant in two minutes: Chat Completion, Custom (OpenAI-compatible), base URL, key and model ID. Plus context size, streaming and reasoning settings for long roleplay.
- How to use Unquant as a Janitor AI proxyUse Unquant as your Janitor AI proxy: the exact proxy URL, model name and API key to enter, plus context and generation settings for unlimited, uncensored roleplay.
- How to connect Open WebUI to UnquantAdd Unquant to Open WebUI as an OpenAI API connection: the URL, key and model list. A private, ChatGPT-style interface on uncensored GLM-5.3-Flash and Qwen 3.8 Flash Next.
- Call Unquant from Python and JavaScript with the OpenAI SDKUse the official OpenAI Python and JavaScript SDKs with Unquant: base URL, streaming, images, tool calling and reasoning control, with copy-paste examples.