Connect Cline to NekoCloud
This guide adapts the tool’s official third-party provider documentation for NekoCloud. It does not imply official certification of this service. NekoCloud has not individually tested the toolchains described here. These are configuration references and acceptance steps for you to perform; no paid requests were made while preparing this guide. Install the tool, create a NekoCloud API key, and confirm the model is available in the model plaza and your key’s group. Replace REPLACE_WITH_MODEL_ID with the exact model ID, not its display name.
Select a third-party provider in extension settings
In VS Code, open Cline sidebar → settings gear → API Provider, then select OpenAI Compatible. This guide does not use official OpenAI sign-in or a Claude subscription login. Record the existing settings or save the current configuration first; edit only the configuration you intend to use without clearing other providers.
| Field | NekoCloud setting |
|---|---|
| API Provider | OpenAI Compatible |
| Base URL | https://api.nekocloud.vip/v1 |
| API Key | REPLACE_WITH_API_KEY, replaced with your own NekoCloud key |
| Model / Model ID | REPLACE_WITH_MODEL_ID, replaced with the exact model ID |
| Use Azure Identity Authentication | Leave disabled; this guide uses a NekoCloud API key |
Enter the key itself in the key field, not an environment-variable name. This page does not assume the UI expands NEKOCLOUD_API_KEY. If the model is absent from the list, use the manual ID entry provided by your version. If that entry is unavailable, check your version and official configuration documentation rather than substituting an unrelated display name.
The official page also lists Max Output Tokens, Context Window, image support, Computer Use, and pricing under Model Configuration. Those are client settings, not statements about a NekoCloud model’s capabilities or prices. Populate them only from confirmed model information. Do not copy another provider’s numbers or enable all tool/image switches merely to save the form. If your UI offers Verify, treat clicking it as potentially sending a request; saving the settings is not an acceptance test.
Save the settings. If your version separates Plan and Act model settings, confirm the mode you intend to use also selects NekoCloud rather than changing only the other mode. Save editor files, run VS Code’s Developer: Reload Window, reopen Cline, and start a new task. Confirm the provider and model that are actually active.
Protocol boundaries
This page uses the third-party OpenAI Compatible Chat Completions configuration. Keep /v1 in the base URL; do not enter the full /v1/chat/completions path. Chat Completions support does not imply Responses or Anthropic Messages support. If an error points to /responses, check your version’s provider implementation and selected route rather than changing only the model name.
NekoCloud’s Anthropic root is https://api.nekocloud.vip. For Anthropic, choose a separate Anthropic provider configuration that supports a custom endpoint and check its URL-building rules. Do not put that root into this guide’s OpenAI field. Validate tool interaction through the read-only test below, not by relying on a text reply or manually checked capability flags.
Acceptance: reply, usage record, and a read-only tool round trip
These steps send model requests and may incur charges. Run them only with your consent. Disable automatic approval, automatic command execution, and unnecessary background requests first. Use a small workspace without sensitive information.
- Start a new conversation, confirm the active provider and model, and send “Reply only OK; do not call tools.” After a normal reply, check the NekoCloud dashboard’s usage records for matching request time, model, and usage/token information. Client cost estimates are not the NekoCloud bill.
- Send “Use only a file-reading tool to read the first few lines of the existing README.md. Return its first line and a one-sentence summary. Do not edit files, run commands, or access the network.” If there is no README.md, choose another existing non-sensitive text file and change the prompt’s path; do not ask the agent to create a file.
- Manually approve that read-only call. Confirm the task trace contains an actual tool name, arguments, and file-reading result, followed by a model answer based on that result. A reply merely claiming to have read the file is not a pass. Check usage records again and verify that the workspace was not modified.
A text reply proves only the chat connection. Matching usage records confirm the request reached the intended account. The tool invocation, tool result, and subsequent model answer must all complete to pass this read-only round trip. If a step fails, stop retrying and retain the request time, model, error code, and redacted request ID rather than repeatedly starting long tasks.
Safety and troubleshooting
Back up existing configuration and merge only the new provider or model entries. Do not replace the whole file or remove other models, rules, tools, or login information. Enter the key itself without a Bearer prefix; REPLACE_WITH_API_KEY is only a placeholder. Never commit real keys, authorization headers, secret-bearing configurations, or sensitive source code to Git, include them in screenshots, or send them to support. Protect local configuration and backup copies too.
For 401 errors, check the active configuration, key, and authentication source. For missing models, check the exact ID and key-group permissions. For 404 errors, check the URL and protocol; avoid duplicate /v1 segments or using a full request path as the base URL. For 429 errors, reduce request frequency according to the response and usage records rather than retrying indefinitely. Do not disable TLS verification, expand execution permissions, or change system network settings to troubleshoot. With Remote SSH, WSL, or containers, ensure configuration and environment variables belong to the host actually running the extension, not just your local terminal.