Knowledge Base Sections ▾

Navigation

▸ Start here By roles

Categories

Tools 36
Glossary 12

jetbrains.tag

JetBrains IDE + JoinGonka Gateway — your own endpoint instead of credits

In the JetBrains ecosystem (IntelliJ IDEA, PyCharm, WebStorm, GoLand, and others), your own inference-endpoint can be connected in two independent ways: the native AI Assistant accepts OpenAI-compatible providers, and GitHub Copilot for JetBrains supports custom endpoints via BYOK as of July 14, 2026. Both ways work with the JoinGonka Gateway: Gonka decentralized network models at live network prices — hundreds of times lower than vendor retail prices, without using subscription credits.

Path 1: Native AI Assistant with an OpenAI-compatible provider

Starting with the 2026.1 release, AI Assistant supports third-party endpoints directly:

1. SettingsSettings → Tools → AI Assistant → Providers & API keys
2. ProviderSelect OpenAI Compatible
3. FieldsBase URL: https://gate.joingonka.ai/v1, API key: your jg-… (issued upon registration with 10M free tokens), then Test Connection
4. ModelsIn the Models Assignment section, assign models to Core features and Instant helpers; set the context window size if necessary

Network models: moonshotai/Kimi-K2.6, MiniMaxAI/MiniMax-M2.7, and deepseek-ai/DeepSeek-V4-Flash-0731 (current list — GET /v1/models). For Core functions with large files, use DeepSeek: 380K context, output up to 32768 tokens.

Tip. The command npx @joingonka/setup --tool jetbrains will print ready-to-use values for the fields below (base URL, key, model ID with current limits) and perform a live request to verify that the gateway accepts them. AI Assistant itself is configured only via the UI — it has no file that can be safely edited, so you must insert the values manually.

Path 2: Copilot for JetBrains with BYOK

If you work via GitHub Copilot in JetBrains-IDE, since July 14, 2026, the plugin supports custom OpenAI-compatible endpoints (public preview, Pro plans and higher): in the plugin settings, add a provider with the endpoint https://gate.joingonka.ai/v1 and your jg-… key — the network models will appear in the switcher next to the built-in ones, and usage will bypass the Copilot premium quota. A detailed breakdown of the BYOK mechanism is 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 charged at current Gonka network prices — see the gateway pricing for current values; there is a unified tariff for all models. The starting 10M free tokens are enough to run AI Assistant on real tasks until the first top-up.

JetBrains-IDE connects to JoinGonka Gateway in two ways: Settings → Tools → AI Assistant → Providers & API keys → OpenAI Compatible (base URL gate.joingonka.ai/v1 + jg- key) — or BYOK in Copilot for JetBrains as of July 2026. Chat and core generation run on network models; Junie and next-edit currently remain on the JetBrains cloud.

Want to learn more?

Explore other sections or start earning GNK right now.

jetbrains.cta.text →