> ## Documentation Index
> Fetch the complete documentation index at: https://docs.globalai.vip/llms.txt
> Use this file to discover all available pages before exploring further.

# ChatWise Setup: Unified Multi-Provider Access via Global AI

> Configure OpenAI, Anthropic, and Gemini providers in ChatWise using a single Global AI token to switch across every major model instantly.

ChatWise lets you configure several providers side by side, which makes it ideal for jumping between GPT, Claude, and Gemini. Fill all three provider API keys with the same Global AI token and you get every mainstream model in one app.

<Warning>
  Before starting, complete the redeem and key-copy steps in [Client overview](/en/clients/overview#before-you-integrate).
</Warning>

Download: [chatwise.app](https://chatwise.app/)

## Configuration

In ChatWise settings, enable the OpenAI, Anthropic, and Google providers and paste the **same Global AI `sk-` token** into each API key field. Set the base URLs as follows:

| Provider                  | Base URL                  |
| ------------------------- | ------------------------- |
| OpenAI (GPT models)       | `https://globalai.vip/v1` |
| Anthropic (Claude models) | `https://globalai.vip`    |
| Google (Gemini models)    | `https://globalai.vip`    |

Return to the chat view and pick a model to start. Copy model IDs from the [pricing page](https://globalai.vip/pricing).

## Troubleshooting

<AccordionGroup>
  <Accordion title="401 / Unauthorized">
    The token was truncated or has a stray space. Recopy it from [/keys](https://globalai.vip/keys) and paste again.
  </Accordion>

  <Accordion title="Connection timeout / cannot connect">
    Most often caused by a running proxy or VPN. Disable all proxy software and retry.
  </Accordion>

  <Accordion title="Model not found">
    The model ID is misspelled or not enabled for your token. Search the [pricing page](https://globalai.vip/pricing) to confirm the exact ID.
  </Accordion>
</AccordionGroup>

## Other OpenAI-compatible clients

Any client that lets you override `base_url` or the API host can connect using the same pattern:

1. **API endpoint**: `https://globalai.vip/v1` (OpenAI format) or `https://globalai.vip` (Anthropic / Gemini format)
2. **API key**: your `sk-` token
3. **Model ID**: copy from the [pricing page](https://globalai.vip/pricing)

Clients such as NextChat, OpenCat, and AMA follow the same recipe. If none of them fit, contact support and we will help you get connected.


## Related topics

- [Global AI Client Integrations: Parameters and Selection](/en/clients/overview.md)
- [WorkBuddy with Global AI: Custom Provider Configuration](/en/clients/workbuddy.md)
- [ChatBox with Global AI: Desktop and Mobile Setup](/en/clients/chatbox.md)
- [Cherry Studio with Global AI: Claude, GPT, Gemini Setup](/en/clients/cherry-studio.md)
- [ChatGPT(Codex) with Global AI: CC Switch or Manual Setup](/en/clients/codex.md)