Gonka24

Continue integration

Use Gonka24 with Continue

Add Gonka24 to Continue with a ready config.yaml that uses OpenAI-compatible Chat Completions for chat, edit, and apply.

Configuration verified August 31, 2026

Connection details

Every example on this page uses the same Gonka24 OpenAI-compatible endpoint, a dashboard API key, and a live model ID.

Base URL
https://api.gonka24.com/v1
Authentication
Bearer sk-...
Model
GET /v1/models

Use a live model ID.

The catalog changes. Call GET /v1/models with your API key and copy an id from the response instead of relying on a model name in a guide.

bash
curl https://api.gonka24.com/v1/models \
  -H "Authorization: Bearer $GONKA24_API_KEY"

Ready-to-use config

~/.continue/config.yaml

Store GONKA24_API_KEY in Continue's local secret mechanism. useResponsesApi: false is required because this integration targets Chat Completions, not /responses.
yaml
name: Gonka24
version: 1.0.0
schema: v1

models:
  - name: Gonka24 coding model
    provider: openai
    model: <model-id-from-/v1/models>
    apiBase: https://api.gonka24.com/v1
    apiKey: ${{ secrets.GONKA24_API_KEY }}
    useResponsesApi: false
    roles:
      - chat
      - edit
      - apply

Set up Continue

  1. Open Continue's local configuration and add the model entry above.
  2. Create the GONKA24_API_KEY secret locally; do not commit the real key in config.yaml.
  3. Replace the model placeholder with an exact ID from GET /v1/models and reload the configuration.
  4. Select Gonka24 coding model for Chat, then test Edit and Apply separately.

What is supported

Supported

Chat, Edit, and Apply roles

The configuration assigns the OpenAI-compatible model only to roles backed by chat completions.
Supported

Streaming

Continue can consume the OpenAI-compatible streaming response returned by Gonka24.
Supported

Agent tool use

Available when the selected model supports OpenAI-style tool calls; validate before enabling destructive tools.
Not included

Responses API and autocomplete

The config explicitly disables /responses. Autocomplete is a separate workload and is not assigned in this verified configuration.

Verify before an agent task

  1. Fetch the model list and copy an exact model ID.
  2. Send a short plain chat request through Continue.
  3. Confirm the request appears in your Gonka24 dashboard activity.
  4. Only then enable tool use, file writes, or long-running agent work.

Troubleshooting

Continue calls /responses: Keep useResponsesApi: false on the model entry, especially for model IDs that Continue identifies as GPT-5 or o-series.
Secret is empty: Define GONKA24_API_KEY in Continue's secret store or temporarily place the key in apiKey to isolate the issue, then move it back to secrets.
Config does not reload: Validate YAML indentation, confirm schema: v1, and use Continue's Reload config action.
Agent mode lacks tools: Add capabilities: [tool_use] only after verifying the selected model returns OpenAI-style tool calls.

Verification sources

Checked against the product documentation below and the Gonka24 public API contract on August 31, 2026.