Knowledge Base Sections ▾
Navigation
▸ Start here By rolesCategories
- Cursor + Gonka AI - cheap LLM for coding
- Claude Code + Gonka AI - LLM for the terminal
- OpenClaw + Gonka AI - affordable AI agents
- OpenCode: your own model in the terminal
- Continue.dev + Gonka AI - AI for VS Code/JetBrains
- Cline + Gonka AI - AI agent in VS Code
- Aider + Gonka AI - pair programming with AI
- LangChain + Gonka AI - AI applications for pennies
- n8n + Gonka AI - automation with cheap AI
- Open WebUI + Gonka AI - your own ChatGPT
- LibreChat + Gonka AI — open-source ChatGPT
- Hermes Agent + DeepSeek on the Gonka network — an autonomous agent for pennies
- Kilo Code + Gonka AI — AI-Agent in VS Code
- Roo Code + Gonka AI — Autonomous AI Agent in VS Code
- LlamaIndex + Gonka AI — RAG applications for pennies
- PydanticAI + Gonka — typed AI agents for pennies
- Vercel AI SDK + Gonka AI — AI applications in TypeScript for pennies
- TanStack AI + Gonka — AI applications in TypeScript for pennies
- API quick start — curl, Python, TypeScript
- JoinGonka Gateway — a full overview
- Management Keys — SaaS on Gonka
- Cheapest AI API: Provider Comparison 2026
- How to buy AI tokens and an API key: 3 methods in 2026
- Cursor Pro request limit reached — breakdown and cheaper alternative
- Claude Code is cheaper — bill breakdown and switching
- Cline is burning money — why the agent spends so much
- OpenClaw is expensive — why the agent burns through tokens and how to save
- OpenRouter: Cheap Alternative — Comparison with JoinGonka Gateway
- Best AI model for coding in 2026: comparison and prices
- Cheap alternative to GitHub Copilot without limits
- A cheap Windsurf alternative without credits or limits
- The cheapest API for AI agents in 2026
- ZCode: Cheap GLM inference instead of GLM Coding Plan
- JetBrains IDE + JoinGonka Gateway — your own endpoint instead of credits
- GitHub Copilot BYOK — own models instead of quotas
- Zed + JoinGonka Gateway — cheap inference in your editor
- Pi + JoinGonka Gateway — terminal agent on cheap inference
- Codex CLI: your own key instead of a subscription
- DeepSeek Harness: Your Own Provider via JoinGonka Gateway
- MiniMax Code: MiniMax agent with your own key via Gonka
- Warp + JoinGonka Gateway — terminal agent on your own endpoint
- Trae + JoinGonka Gateway — Gonka network models in AI-IDE
- Cherry Studio + JoinGonka Gateway — desktop AI client
- omp (Oh My Pi) + JoinGonka Gateway: an agent with model roles
- OpenHands + JoinGonka Gateway: agent on your own endpoint
- Qwen Code after the closure of qwen-oauth: working via JoinGonka Gateway
- Goose + JoinGonka Gateway: your own provider and key in the keyring
- Crush + JoinGonka Gateway: Charm agent on Gonka network models
- Zoo Code + JoinGonka Gateway: Migrating from Roo Code to Gonka models
- Kimi Code CLI: Moonshot AI agent on your key via Gonka
- Factory Droid + JoinGonka Gateway: BYOK on Gonka network models
- MiMo Code + JoinGonka Gateway: Xiaomi agent on Gonka network models
Tools
Open WebUI + Gonka AI - your own ChatGPT
Open WebUI is the most popular self-hosted ChatGPT interface. Beautiful UI, chat history, multimodality, RAG, custom prompts, support for multiple models. It can be deployed in 5 minutes via Docker.
Open WebUI supports OpenAI-compatible APIs. By connecting the JoinGonka Gateway, you get a full-fledged ChatGPT equivalent for your team — for $0.0069/1M tokens. The Gateway also supports the Anthropic API (/v1/messages), which extends compatibility with ecosystem tools. No subscriptions ($20/mo for ChatGPT Plus), no limits, full data control.
Step 1: Get API Key and Deploy Open WebUI
API key: sign up at gate.joingonka.ai/register, get 3M free tokens, create a jg-xxx key.
Docker installation of Open WebUI:
docker run -d \
--name open-webui \
-p 3000:8080 \
-e OPENAI_API_BASE_URL=https://gate.joingonka.ai/v1 \
-e OPENAI_API_KEY=jg-your-key \
-v open-webui:/app/backend/data \
ghcr.io/open-webui/open-webui:mainOpen http://localhost:3000 — Open WebUI is ready to go.
Without Docker: if Docker isn't installed, Open WebUI can be deployed via pip:
pip install open-webui
OPENAI_API_BASE_URL=https://gate.joingonka.ai/v1 \
OPENAI_API_KEY=jg-your-key \
open-webui serveStep 2: Configure via UI
If you deployed Open WebUI without env variables, configure it through the interface:
- Open Open WebUI → Create an admin account.
- Go to Admin Panel → Settings → Connections.
- In the OpenAI API section:
- API URL:
https://gate.joingonka.ai/v1 - API Key:
jg-your-key
- API URL:
- Click Save.
- In the model list, select
MiniMaxAI/MiniMax-M2.7.
For teams: create accounts for your colleagues. Each gets their own chat interface, history, and personal prompts — but everyone uses a single API key and a single JoinGonka balance.
Features:
- Markdown rendering with code highlighting
- Document upload for analysis (RAG)
- Custom system prompts
- Chat export/import
- Mobile interface
Open WebUI vs ChatGPT Plus
Comparing Open WebUI + Gonka with a ChatGPT Plus subscription:
| Parameter | Open WebUI + Gonka | ChatGPT Plus |
|---|---|---|
| Price/month (1 user) | ~$0.30 | $20 |
| Price/month (10-person team) | ~$3.00 | $200 ($250 Team) |
| Message limits | None | 40-80 GPT-5.5 per 3 hours |
| Self-hosted | Yes (Docker) | No |
| Data privacy | Full (your server) | Data on OpenAI servers |
| Custom prompts | No limits | Limited |
| Model choice | Any OpenAI-compatible | Only OpenAI models |
| RAG (documents) | Built-in | Limited |
| Max response length | up to 8192 tokens (DeepSeek V4 Flash up to 32768) | 16K+ tokens |
Open WebUI + Gonka is 60-80 times cheaper than ChatGPT Plus for a single user, and even more profitable for teams. At the same time, you get full control over data, no limits, and customization.
Alternative self-hosted ChatGPT interface: LibreChat.