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
LibreChat + Gonka AI — open-source ChatGPT
LibreChat is an open-source ChatGPT clone with support for multiple LLM providers simultaneously. Switch between models in one interface: Gonka, OpenAI, Anthropic, local models. Plus: plugins, preset prompts, multi-user support, Docker deploy.
LibreChat supports both OpenAI-compatible APIs and the Anthropic API. JoinGonka Gateway provides both formats — /v1/chat/completions (OpenAI) and /v1/messages (Anthropic) — with a single key. Connection is one line in .env.
The result: a powerful ChatGPT alternative for the team for $0.0069/1M tokens, with support for both API formats.
Step 1: Deploy LibreChat
Docker Compose — the recommended installation method:
# Clone the repository
git clone https://github.com/danny-avila/LibreChat.git
cd LibreChat
# Copy the env file
cp .env.example .envJoinGonka API key: sign up at gate.joingonka.ai/register, get 3M free tokens, create a jg-xxx key.
Step 2: Configure Gonka as a provider
Edit the .env file in the root of LibreChat:
# .env
OPENAI_API_KEY=jg-your-key
OPENAI_REVERSE_PROXY=https://gate.joingonka.ai/v1/chat/completions
OPENAI_MODELS=MiniMaxAI/MiniMax-M2.7Run:
docker compose up -dOpen http://localhost:3080 — LibreChat is ready.
Multi-model support: LibreChat lets you connect multiple providers. You can keep the native OpenAI API for specific tasks, add a local model via Ollama, and use Gonka as your main low-cost provider — all in one interface.
For advanced configuration, use librechat.yaml:
# librechat.yaml
endpoints:
custom:
- name: "Gonka"
apiKey: "jg-your-key"
baseURL: "https://gate.joingonka.ai/v1"
models:
default:
- "MiniMaxAI/MiniMax-M2.7"
titleConvo: true
titleModel: "MiniMaxAI/MiniMax-M2.7"LibreChat vs Open WebUI
Two of the best self-hosted ChatGPT interfaces — let's compare:
| Parameter | LibreChat | Open WebUI |
|---|---|---|
| Multimodality | Built-in (UI toggle) | Built-in |
| Plugins | Yes (ecosystem) | Yes (extensions) |
| RAG | Via plugins | Built-in |
| Docker | docker compose | Single container |
| Interface | Maximum ChatGPT-like | Custom style |
| Community | 30K+ GitHub stars | 40K+ GitHub stars |
| Configuration | .env + librechat.yaml | UI + env |
Both work perfectly with JoinGonka Gateway. LibreChat is closer to ChatGPT in terms of UX and is better for teams with multiple providers. Open WebUI is easier to deploy (single container) and features built-in RAG. The choice is a matter of preference.
Model parameters via JoinGonka: context window — 200K tokens for MiniMax M2.7 (380K for DeepSeek V4 Flash, 390K for GLM-5.3 Flash), max response length — up to 8192 tokens (for DeepSeek V4 Flash — up to 32768). For longer responses, choose DeepSeek V4 Flash or connect additional providers in LibreChat.