$1 in → $2 of model usage, at provider rates

One AI coding subscription.
Every model.
Three flat prices.

DevPass turns every dollar into $2 of model usage at provider rates — metered transparently, with no token math and no lock-in. Best in DevPass Code, our first-party agent, and drop-in for every OpenAI-compatible tool.

First-month guarantee — barely used it? Refund yourself in one click from your billing dashboard, up to 14 days after your first purchase.

~ devpassbash
$ devpass-code auth login
# opens your browser — no keys to copy, models built in
$

Works with every agent

DevPass CodeClaude CodeOpenCodeEmpryoSoulForgeSoulForgeAutohandClineCursorAiderContinueany OpenAI-compatible tool
DevPass CodeClaude CodeOpenCodeEmpryoSoulForgeSoulForgeAutohandClineCursorAiderContinueany OpenAI-compatible tool
DevPass CodeClaude CodeOpenCodeEmpryoSoulForgeSoulForgeAutohandClineCursorAiderContinueany OpenAI-compatible tool
DevPass CodeClaude CodeOpenCodeEmpryoSoulForgeSoulForgeAutohandClineCursorAiderContinueany OpenAI-compatible tool

0+

Models

0+

Providers

0×

Usage value

Runs on the open-source LLM Gateway — 1T+ tokens routed · 1.6K+ GitHub stars

The meter

What you pay vs. what you get

Every plan includes the full 100+ model catalog. The only things that change are your monthly usage allowance, its daily pacing, and the weekly fair-use cap on premium models.

Lite

For evenings-and-weekends coding

$29/mo

≈ $0.97/day · switch or cancel anytime

2× usage

Worth 2× what you pay in model usage, metered at provider list rates.

Model catalog
100+ models
Daily pacing
8% of credits / day
Frontier fair-use
10% of credits / week
Unused carries over
up to $29
Support
Email
  • All 100+ models — Claude, GPT-5, Gemini, GLM, Qwen, …
  • DevPass Code, Claude Code, OpenCode, Empryo, SoulForge & any OpenAI-compatible tool
  • Real-time dashboard with per-request cost
Get Lite

14-day self-serve refund · no lock-in

Most popular

Pro

For daily development work

$79/mo

≈ $2.63/day · switch or cancel anytime

2× usage

Worth 2× what you pay in model usage, metered at provider list rates.

Model catalog
100+ models
Daily pacing
9% of credits / day
Frontier fair-use
12% of credits / week
Unused carries over
up to $79
Support
Priority
  • Everything in Lite
  • Headroom for a full agent session every day
  • More frontier fair-use headroom than Lite
Get Pro

14-day self-serve refund · no lock-in

Max

For all-day, multi-agent workloads

$179/mo

≈ $5.97/day · switch or cancel anytime

2× usage

Worth 2× what you pay in model usage, metered at provider list rates.

Model catalog
100+ models
Daily pacing
10% of credits / day
Frontier fair-use
15% of credits / week
Unused carries over
up to $179
Support
Front of queue
  • Everything in Pro
  • Run agents non-stop without watching the meter
  • Best frontier-model allowance per dollar
Get Max

14-day self-serve refund · no lock-in

Daily pacing spreads your allowance across the cycle: each rolling 24-hour window can use the share of monthly credits shown on the card, across every model. Frontier fair-use covers premium models — any model priced at $5+ per million input tokens or $15+ per million output tokens after any active public discount — as a weekly allowance on top. Every other model draws on your full monthly allowance, and what you leave unused at renewal carries into the next cycle up to the amount on the card. No hidden throttling. And none of it is a wall: opt into pay-as-you-go overflow in your dashboard to keep coding past any of them, billed from a credits balance at provider rates.

First-month guarantee

Try DevPass for real. If it's not for you, refund yourself from Billing in your dashboard — a full refund of your first month, up to 14 days after purchase, as long as you've used less than 10% of your allowance. One click, no email, no cancellation fee.

No subscription? Pay as you go

The same 100+ models are on LLM Gateway without a plan — top up credits and pay per token at provider rates with a flat 5% platform fee, or bring your own provider keys for free. DevPass simply doubles every dollar.

Use pay-as-you-go

Need company/address details on your invoice? Update billing settings before purchase. We email the invoice automatically after payment.

Usage is metered at each provider's published per-token rate. Every request shows its dollar value in your dashboard in real time.

Price check

API pay-as-you-go
$29 → $29 of usage
Cursor Pro
$20/mo → about $20 of usage
DevPass Lite
$29/mo → $58 at provider rates

Same dollars, 2× the metered usage — in whatever editor or agent you already use.

See the full DevPass vs Cursor comparison

Passport control

One passport. Every agent stamped in.

DevPass Code — our own terminal agent — is the bearer: one-click browser login, no keys to copy. Claude Code, OpenCode, Empryo, and every OpenAI-compatible tool get stamped in with two env vars.

Tap the passport to open it.

Claude Code

Two env vars and Claude Code routes through LLM Gateway. Use any model — Claude, GPT-5, Gemini, GLM — and switch mid-session with /model.

ANTHROPIC_BASE_URL + AUTH_TOKEN

OpenCode

LLM Gateway is built into OpenCode. Run `opencode`, type `/connect`, paste your DevPass key. No env vars, no config files.

/connect → LLM Gateway

Empryo

The AI coding agent that edits symbols, not strings. Maps your repo on launch and edits by symbol name. Run `empryo`, type `/keys`, paste your DevPass key.

/keys → paste your key
SoulForge

SoulForge

Graph-powered coding agent. Maps your repo on launch and edits TypeScript by symbol name, not by find-and-replace. Run `soulforge`, type `/keys`, paste your DevPass key.

/keys → paste your key
+ Cline, Cursor, Aider, Continue & any OpenAI-compatible tool

How it works

Up and running in minutes

01

Pick a plan

Choose Lite, Pro, or Max. Your DevPass key works everywhere — no separate keys per tool.

02

Plug it into your agent

Two env vars for Claude Code, /connect in OpenCode, /keys in Empryo. No SDK changes, no code refactor.

03

Switch models freely

Claude Opus 4.8 for architecture, GPT-5.5 for review, Gemini 3.1 Pro for fresh eyes — same key, no extra cost.

The latest flagships

Every plan ships with the newest models

Claude Opus 4.8, Gemini 3.1 Pro, GPT-5.5, plus the strongest open-weight Chinese coders — included on every tier.

Every request is smart-routed to the best provider in real time — picking a specific provider isn't possible on DevPass. If you need provider pinning, use LLM Gateway's pay-as-you-go API instead.

FAQ

Common questions

Everything you need to know about usage limits, plans, and getting started with DevPass.

Can't find an answer? Contact us

Every plan includes a fixed monthly usage allowance, calculated at standard provider rates:

  • Lite — $29/mo: $58 in monthly model usage
  • Pro — $79/mo: $158 in monthly model usage
  • Max — $179/mo: $358 in monthly model usage

That's 2× the subscription price — model access at a discount compared to paying providers directly, with a bill that never moves.

Stop watching your token balance

Pick a plan, set two env vars, get back to building.

Self-serve first-month refund · no lock-in · no cancellation fee