Skip to main content
The Electron Hub Coding Plan (DevPass) is built for coding agents and CLI tools (Claude Code, Cline, Roo Code, Cursor, and anything OpenAI/Anthropic-compatible). Unlimited token usage on a flat monthly price. No credits. No per-token bill. You keep coding; we never hard-stop you for burning tokens. You get a dedicated ek-dev- API key that is fully independent of any other Electron Hub plan.

​
Tiers

Launch seats are capped per tier. If a tier is sold out, join the waitlist on the dashboard — you’ll be notified when a seat opens (first come, first served).

​
Included Models

All models support function calling on /v1/chat/completions, /v1/messages, and /v1/responses. Reasoning is available on every :dev model except qwen3.6-27b:dev. Series weight (0.5× / 1× / 2×) only affects soft full-speed headroom (ceil(raw × weight)), not whether you can keep using the plan. Dashboard per-model stats stay raw.
:dev models accept only ek-dev- keys, and DevPass keys can call only :dev models. Keep your master key configured if you need the rest of the catalog.

​
Quickstart

  1. Subscribe on the Dashboard → Console → Coding Plan.
  2. Your ek-dev-... key is provisioned within seconds and always retrievable from the Coding Plan tab (regenerating it instantly kills the old key everywhere).
  3. Use it as a Bearer token:

​
Fair Use

Plans are for individual coding: one human working interactively in the tools they already use. Unlimited tokens, flat monthly price, and a key that is yours alone — every machine you own, never shared. Token usage is never hard-capped. Elevated usage is slowed or reordered so interactive subscribers stay responsive when the platform is busy. Live status is always on the dashboard’s Coding Plan tab.
Each plan allows a set number of requests running at the same time (2 on Lite, 5 on Turbo) — there is no requests-per-minute limit. If all your slots are busy, you get a 429 with a Retry-After header; wait for one to finish and retry. Coding agents handle this automatically.
Each plan includes generous full-speed headroom that resets at 21:00 UTC. Going past it never blocks you — requests continue with reduced concurrency and paced admission (consumption-scaled inter-request spacing, up to about a minute when far into overage) until the reset. Your dashboard shows how close you are to full-speed headroom.
A rolling weekly soft headroom sits above the daily one. Past it, the same slow lane applies (lower concurrency + paced admission) — not a hard stop. This keeps sustained 24/7 grinders from crowding out interactive work across the week.
Firing a very large number of request starts within a few seconds may get a brief 429. Normal coding-agent workloads fit comfortably.
Repeatedly hitting the parallel-slot limit (hundreds of concurrency 429s in a usage day) can temporarily pause admission for a few hours. While paused, requests return 403. Your key stays valid; service resumes automatically at the time shown on the dashboard. Regenerating the key clears an automatic concurrency pause.

​
Low-interactivity mode

Plans are sized for a person coding, even intensively, all day. On rare occasions when an account shows an unusual usage pattern far beyond typical interactive work, the plan enters low-interactivity mode for about 24 hours:
  • Under light load, behavior is unchanged.
  • When the platform is busy, requests may be queued behind interactive sessions and may occasionally need a retry.
  • Nothing is blocked. Your plan, models, and answer quality stay the same.
  • Interactive mode resumes automatically at the time shown on the Coding Plan tab — no action is required.
Low-interactivity mode is a temporary fairness control so interactive subscribers keep responsive access during busy periods. It is not a suspension. If this ever surprises you, check for a runaway automation first, then ask us on Discord. Workloads that need unattended or high-duty-cycle throughput are a better fit for a regular Electron Hub API key billed on credits.

​
Fair use, in one paragraph

Plans are individual, for a human coding interactively. Your key can run on every machine you own, and usage simply adds up across them. What it cannot do is serve other people or power shared/unattended workloads: no sharing with teammates, no pooling behind a proxy, no reselling, no deployed apps or backends riding a plan key. That is what makes the flat price work. Accounts with clearly non-individual usage patterns may lose access. If you are not sure which side of the line your setup is on, ask us on Discord — the answer is usually that you are fine.

​
Errors

​
Terms

  • Monthly billing via Creem, auto-renewing, non-refundable. Cancel any time — your key stays active until the period ends.
  • Individual use only. Sharing or reselling a key leads to suspension; chargebacks are treated as account-level violations.
  • Home, work, laptop, CI, VPNs — all fine. Enforcement targets resale patterns, not normal developer life.

​
FAQ

Yes. There is no hard token cap and no per-token charge. Soft full-speed headroom only affects concurrency and latency when you are far past typical interactive use — requests are never blocked for burning tokens.
Yes. Founding / beta subscribers who purchased at the launch rate keep that price for as long as the subscription stays active. If you cancel and subscribe again later, the current public price applies.
Yes — change plans in the Creem billing portal. Your existing key picks up Turbo limits automatically.
Your ek-dev- key is deactivated. Resubscribe any time to restore it.
See Low-interactivity mode. Requests remain available; under load they may queue behind interactive sessions until interactive mode resumes automatically.