Cline
Settings for using Echo Token Station models from the VS Code extension Cline.
Cline is an AI coding extension that runs in editors such as VS Code. It connects to Echo with Cline's "OpenAI Compatible" provider (a setting for services that support the OpenAI format). This way, you can type in an Echo model ID and select it.
Tested: No (as of 2026-09-27). The steps on this page are based on Cline's official documentation.
What you need
- Your Echo API key (a string that starts with
sk-) - The ID of the model you want to use (for example
deepseek-flash) and that model's context length (the number of tokens the model can handle at once). You can find them in the model list
Set up
- Open the settings (the gear icon) in Cline
- In "API Provider", choose "OpenAI Compatible"
- Enter the following
| Setting | Value |
|---|---|
| Base URL | https://token.echohub.io/v1 |
| API Key | Your Echo API key |
| Model | The ID of the model to use (for example deepseek-flash) |
- Open "Model Configuration" and fill it in for the model you use
| Setting | Value |
|---|---|
| Context Window size | The context length on the model's page |
| Max Output Tokens | The maximum output tokens on the model's page |
| Image Support | On only for models whose page says they accept image input |
| Input Price, Output Price | Used to show an estimated cost in Cline. Leaving them empty does not affect calls. Check what Echo charges in 「利用状況」 (Usage) in the console |
Leave "Use Azure Identity Authentication" off.
When you call a Claude model this way, the request is converted from the OpenAI format. In that case, structured output (specifying a JSON shape with response_format) has no effect.
Check that it works
Ask Cline a simple question. If an answer comes back, you are done. The call also appears in 「呼び出し履歴」 (Call history) in the console.
Troubleshooting
| Symptom | Cause | Fix |
|---|---|---|
| 404 with an HTML page instead of JSON | The Base URL does not end with /v1 | Change it to https://token.echohub.io/v1 |
401 and Invalid API key | The key is wrong, stopped or expired, or has used up its spending limit | Check the key's status in the console |
403 and Insufficient balance | Insufficient balance | Top up |
404 and Invalid URL | The Base URL has /v1 twice, or goes on to /chat/completions | Change it to https://token.echohub.io/v1 |
503 and The model … does not exist or is not available | The model ID is wrong, or Echo does not offer the model | Check the model ID |
The list of error bodies is in Errors and fixes.
Choosing the Anthropic provider
You can also choose "Anthropic" in Cline's "API Provider" and enter https://token.echohub.io in "Use custom base URL". In that case, you choose the model from Cline's list. If Echo offers a model ID from that list, it is expected to work, but we have not tested it.
Sources
| What | Source | Checked |
|---|---|---|
The setting names of OpenAI Compatible, including /v1 in the Base URL | https://docs.cline.bot/provider-config/openai-compatible | 2026-09-26 |
| "Use custom base URL" for Anthropic, choosing the model from the list | https://docs.cline.bot/provider-config/anthropic | 2026-09-26 |
| HTTP statuses and error bodies on Echo's side, structured output not working when a Claude model is called in the OpenAI format | Measured in Echo's test environment (without Cline) | 2026-09-27 |