Cline

Open-source coding agent for VS Code using OneProvider's OpenAI-compatible API.

Cline coding agent for VS Code

What works

Cline sends OpenAI-compatible text and coding-agent requests through OneProvider with a compatible model ID you select from the catalog.

Client limitation

Image, tool-use, and context capabilities depend on the exact selected model; verify with a small text task first.

Setup

1. Choose OpenAI Compatible

   In Cline API Provider settings, choose OpenAI Compatible and paste your OneProvider key.

   API Provider: OpenAI Compatible
   API Key: sk-your-key-here

2. Set the custom base URL

   Set the base URL to https://api.oneprovider.dev/v1 and the exact model ID to gpt-5.6-terra.

   Base URL: https://api.oneprovider.dev/v1
   Model ID: gpt-5.6-terra

3. Start a small text task

   Open a new Cline session and request one small read-only explanation before enabling model-specific capabilities.

Verify the connection

Confirm the request in Dashboard Usage

The request should show the configured model and a settled OpenAI-compatible usage row.

Connection details

Protocol

openai-chat

Endpoint

https://api.oneprovider.dev/v1

Key security

Use a dedicated key with model, rate, spend, and expiry limits; never commit the key in workspace settings.

Which model to choose

Cline uses the OpenAI Compatible provider, so enter the model id exactly as in the catalog . gpt-5.6-terra is a balanced default for coding tasks, gpt-6.1-sol suits large multi-file work, gpt-5.6-luna is cheap for quick questions. Claude ids also work through the same provider, for example claude-sonnet-5-5. Image input, tool use and context size depend on the exact model, so start with one small read-only task. If Cline asks for a context window or max output, copy the values from the model row in the catalog.

Common errors and fixes

404 or “Invalid URL”

Base URL must be https://api.oneprovider.dev/v1: with /v1, without /chat/completions.

401 Unauthorized

The key is missing a character or has a space or quote around it, or the balance is empty. Paste the whole key again and check the cabinet.

“Model not found” or a 400 about the model

The id has a typo or is not in the catalog. Copy it from the models page; the match is exact and case-sensitive.

429 “Insufficient balance”

The balance or the key’s spend limit is used up. Retrying does not help: top up or raise the limit.

The agent stops after one step

The selected model may not support tool calls well. Pick a frontier or balanced model and keep the task small.

Streams break or hang

Turn off VPN or VLESS proxies: they buffer SSE. OneProvider itself does not.

FAQ

Which provider do I choose in Cline?

OpenAI Compatible. Paste the OneProvider key and the base URL above.

Can I use Claude models in Cline?

Yes, enter a Claude id in the same OpenAI Compatible provider, or use Cline’s Anthropic provider with the custom base URL https://api.oneprovider.dev if your version offers it.

Is my key stored in the repository?

No, Cline keeps it in VS Code’s secret storage. Still, use a dedicated key with a spend limit and never commit it in workspace settings.

Where do I see usage?

In the dashboard Usage page: each request shows the model and a settled charge.

Quick answers

Which base URL do I use?

Claude Code and Anthropic SDKs use https://api.oneprovider.dev. OpenAI SDKs and OpenAI-compatible clients use https://api.oneprovider.dev/v1. One key works behind both; the model list is on the models page ; rates are on the pricing page .

How do I authenticate?

Send the raw sk-… key in x-api-key or Authorization: Bearer: one of them, never both. Keep the key in an environment variable, not in a file that gets committed. More on authentication .

Where do I get a key?

Open your cabinet in the Telegram bot @oneprovider_robot or at app.oneprovider.dev, top up the balance and press “Issue a key”. Each key can carry its own spend limit. Cabinet & API keys .

What do 401, 404 and 429 mean?

401: the key is missing, mistyped or sent in the wrong header; paste the whole key without quotes or spaces. 404: usually a wrong base URL, for example a missing or doubled /v1. 429 with “Insufficient balance”: the cabinet balance or the key’s spend limit is used up, so top up instead of retrying; any other 429 is a rate limit, so wait for Retry-After. Details: error codes and troubleshooting .

Why do streams cut off or reset?

VPN and VLESS proxies often buffer SSE or break HTTP/2 negotiation. OneProvider has no regional restrictions and does not buffer streams, so turn the proxy off and retry.

Where do I ask if this is not enough?

Message @Oneproviderhelpbot on Telegram or open “Support” in the web cabinet, with the HTTP status code and the exact error message. How support works .