Zed + JoinGonka Gateway — cheap inference in your editor

Zed is a fast open-source editor with an Agent Panel that supports any OpenAI-compatible provider: just specify your api_url and a list of models. This means Zed's agent functions can run on models from the decentralized Gonka network via JoinGonka Gateway — at real-time network prices, hundreds of times lower than vendor card prices, with 10M free starter tokens and no credit card required.

Step 1: Get a JoinGonka key

Register on the gateway and create a key starting with jg-…. The current list of network models is always available via GET https://gate.joingonka.ai/v1/models; currently, these are moonshotai/Kimi-K2.6, MiniMaxAI/MiniMax-M2.7, and deepseek-ai/DeepSeek-V4-Flash-0731.

Step 2: Add a provider via UI or settings.json

Via installer (fastest):

npx @joingonka/setup --tool zed

It will add the provider and model catalog directly to settings.json, preserving your comments and other editor settings. The key is not placed there—Zed does not read it from there (see below).

Via UI: open agent settings (command agent: open settings) → in the «LLM Providers» section, click Add Provider → fill in the fields: provider name, api_url = https://gate.joingonka.ai/v1, key jg-… and models. The key goes into the system storage (keychain), not the text config.

Via settings.json (command zed: open settings) — block language_models.openai_compatible:

`api_url`	`https://gate.joingonka.ai/v1`
`available_models`	array of models; for each — `name`, `max_tokens` (this is CONTEXT, not output limit) and `max_output_tokens`

Correct limits for network models: DeepSeek V4 Flash — context 380000, output 32768; Kimi K2.6 and MiniMax M2.7 — context 200000, output 8192.

Key. It is not written to settings.json — Zed documentation explicitly forbids it, and there is no field for it in the schema. Provide the key in one of two ways: via the environment variable JOINGONKA_API_KEY (Zed derives the name from the provider id) or paste it in the provider panel — then it will be stored in the keychain.

Step 3: Select a model and start working

The added models appear in the Agent Panel model selector, where you can pick a model for your conversation. All three network models support tool calling, so Zed's agent functions (code edits, multi-step tasks) work as expected. For large repositories and long sessions, use DeepSeek V4 Flash: it offers the longest network context and output up to 32768 tokens.

What works on a custom endpoint and what doesn't

Agent Panel, chat, and inline assist work with your provider. Edit predictions (Zeta autocomplete) remain on Zed's own models — third-party APIs cannot be connected there; this is a limitation of the editor, not the gateway. Vision tasks do not work through the gateway: network models are text-based.

How much does it cost

Inference is charged based on live Gonka network prices — see the gateway pricing list for current values. A unified rate for all network models and 10M free starter tokens allow you to test the Zed agent on real tasks before your first top-up.

Zed connects to JoinGonka Gateway in a couple of minutes: Add Provider in agent settings (or settings.json block) → api_url gate.joingonka.ai/v1 → key jg- in keychain → network models in the Agent Panel selector. Edit predictions remain on Zed's models; everything else runs on cheap Gonka inference.

← GitHub Copilot BYOK — own models instead of quotas Pi + JoinGonka Gateway — terminal agent on cheap inference →

Want to learn more?

Explore other sections or start earning GNK right now.

zed.cta.text →