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
JetBrains IDE + JoinGonka Gateway — your own endpoint instead of credits
In the JetBrains ecosystem (IntelliJ IDEA, PyCharm, WebStorm, GoLand, etc.), a custom inference-endpoint can be connected in two independent ways: the native AI Assistant accepts OpenAI-compatible providers, and GitHub Copilot for JetBrains, as of July 14, 2026, supports custom endpoints via BYOK on all plans. Both methods work with the JoinGonka Gateway: use Gonka decentralized network models at real-time network prices — hundreds of times lower than vendor card prices, without using up subscription credits.
Path 1: Native AI Assistant with an OpenAI-compatible provider
Starting from the 2026.1 series, AI Assistant supports third-party endpoints directly:
| 1. Settings | Settings → Tools → AI Assistant → Providers & API keys |
| 2. Provider | Select OpenAI Compatible |
| 3. Fields | Base URL: https://gate.joingonka.ai/v1, API key: your jg-… (issued upon registration with 3M free tokens), enable the Tool calling toggle (without it, the model will not receive MCP tools), then Test Connection and Apply |
| 4. Models | In the Models Assignment section, assign models to Core features and Instant helpers, and set the Context window: the standard 64,000 tokens is three times smaller than the shortest network window. Real values are 200000 for MiniMax M2.7, 380000 for DeepSeek V4 Flash, 390000 for GLM-5.3 Flash |
Network models: MiniMaxAI/MiniMax-M2.7, deepseek-ai/DeepSeek-V4-Flash-0731, and zai-org/GLM-5.3-Flash (current list — GET /v1/models). For Core features with large files, use DeepSeek: 380K context, output up to 32,768 tokens.
Tip. The npx @joingonka/setup --tool jetbrains command will print the ready values for these fields — base URL, key, model ID, and its real limits (context window and output limit) — and will test that the gateway accepts them with a live request. The AI Assistant itself can only be configured via the UI — it lacks a configuration file that can be safely edited, so values must be pasted manually.
Path 2: Copilot for JetBrains with BYOK
If you use GitHub Copilot in JetBrains-IDE, since July 14, 2026, the plugin has supported custom OpenAI-compatible endpoints on all Copilot plans: open Copilot Chat → model list → Manage Models, select a provider with an OpenAI-compatible endpoint, click Add Models, and enter the Base URL https://gate.joingonka.ai/v1, your jg-… key, and the model ID. Click Save, check the model under your key, and save again — the network models will appear in the selector next to the built-in ones, and usage will not count towards your Copilot request quota. A detailed breakdown of the BYOK mechanics can be found in our GitHub Copilot BYOK guide.
Limitations — honestly
Custom providers in AI Assistant cover chat and core generation, but as of 2026.1, they do not work for Junie (JetBrains agent) and next-edit suggestions — these functions remain on the JetBrains cloud. Inline autocomplete on a third-party model requires compliance with the prompt scheme/FIM format — network chat models are strongest specifically in chat and agent scenarios. Vision tasks do not work through the gateway: the models are text-only.
Which path to choose
No Copilot subscription? Choose path 1: native AI Assistant with the 2026.1 free tier plus cheap gateway inference for chat and generation. Already paying for Copilot? Path 2 offloads your premium quota for agent sessions. The paths are independent: the provider for completion functions is configured separately from the chat provider; they can be combined.
Cost
Inference is billed at live Gonka network prices — see current values in the gateway price list; the rate is uniform for all models. The starting 3M free tokens are enough to run AI Assistant on your first tasks before topping up.