[BUG] Gemini 3 error on kie.ai

[kangarko]

I want to use kie.ai, specifically https://kie.ai/gemini-3-pro as a custom API provider for Gemini.

I tried putting custom base url to https://api.kie.ai/gemini-3-pro/v1/chat/completions or just https://api.kie.ai/gemini-3-pro/ but I am getting the error below. I left API provider to Google Gemini.

I think there needs to be greater freedom in customizing the base url to allow third party routers.

App Version

0.0.7843 (6e08ae4)

Relevant logs or errors (optional)

{
  "error": {
    "timestamp": "2026-01-27T17:41:22.309Z",
    "version": "0.0.7843",
    "provider": "gemini",
    "model": "gemini-3-pro",
    "details": "Gemini generate context stream error: {\"timestamp\":1769535679408,\"status\":404,\"error\":\"Not Found\",\"message\":\"No message available\",\"path\":\"/gemini-3-pro/v1beta/models/gemini-3-pro-preview:streamGenerateContent\"}"
  },
  "history": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "<user_message>\nwhasup\n</user_message>"
        },
        {
          "type": "text",
          "text": REDACTED
        }
      ],
      "ts": 1769535677628
    }
  ]
}

I've analyzed this issue and need some clarification to determine the best solution.

Current Situation:
The "Google Gemini" provider uses the official @google/genai SDK, which has a fixed API path structure (e.g., /v1beta/models/{model}:streamGenerateContent). When you set a custom base URL, the SDK appends these paths automatically, which causes the 404 error you're seeing with kie.ai.

Question: Does kie.ai provide an OpenAI-compatible API?

Based on the URL you tried (https://api.kie.ai/gemini-3-pro/v1/chat/completions), it looks like kie.ai might expose an OpenAI-compatible API format rather than the native Gemini API format.

If so, you can already use kie.ai today by selecting "OpenAI Compatible" as your API provider instead of "Google Gemini", with these settings:

• Base URL: https://api.kie.ai/gemini-3-pro/v1
• Model ID: The model name kie.ai expects (e.g., gemini-3-pro)
• API Key: Your kie.ai API key

Could you please clarify:

1. Does kie.ai provide an OpenAI-compatible API (with /v1/chat/completions endpoint)?
2. Have you tried using the "OpenAI Compatible" provider with the settings above?
3. If you've tried it and it doesn't work, what error do you get?

If kie.ai does use the OpenAI-compatible format, this would be a documentation/UX issue rather than a code change. If kie.ai uses a different API format, please let me know and I can propose the appropriate solution.

Please tag @roomote in your response with the answers, and I'll be happy to proceed accordingly.

[kangarko]

@roomote it does work partially, but I am getting:

Date/time: 2026-01-27T17:55:49.701Z
Extension version: 0.0.7843
Provider: openai (proxy)
Model: gemini-3-pro

XML tool calls are no longer supported. Remove any XML tool markup (e.g. <read_file>...</read_file>) and use native tool calling instead.

Thanks for the update @kangarko! I can see the issue now. The error "XML tool calls are no longer supported" indicates that the Gemini 3 model via kie.ai is not properly using OpenAI's native function calling API and is instead outputting XML-formatted tool calls in its text response.

This happens when:

1. The API proxy doesn't fully support OpenAI's function/tool calling feature
2. The model behind the proxy doesn't understand how to use the native tool calling format

I'll work on improving the error message to be more helpful for users encountering this situation, and provide clearer guidance on what's happening and potential workarounds.

Will open a PR shortly with my attempt at addressing this.

Opened PR #11012 with my attempt at addressing this.

The PR improves the error messages to be more user-friendly when an API provider does not fully support native function/tool calling. Instead of the confusing "XML tool calls are no longer supported" message, users will now see:

"The model is outputting XML-formatted tool calls instead of using native function calling. This typically happens when your API provider does not fully support OpenAI's function/tool calling feature. Please verify that your API provider supports native tool calling, or try using a different provider."

This should help users better understand what's happening and what options they have.

Feedback welcome!

[kangarko]

@roomote this is not the proper fix, the proper fix would be to adapt for the new Gemini 3 Pro scheme which kie.ai uses

Thanks for the feedback @kangarko! I understand that improving error messages is not the proper solution here.

I'll explore how to adapt the codebase to properly handle the Gemini 3 Pro scheme that kie.ai uses. From what I understand, this involves supporting XML-formatted tool calls that the model outputs when using kie.ai as a proxy.

I'll investigate the current tool call handling and work on adding proper support for this format. Will share progress in a new PR.