One key.
Every model.
Three flat prices.
DevPass turns every dollar into $3 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 — cancel within 7 days of your first purchase and we refund your first month, minus metered usage.
Works with every agent
SoulForgeAutohandClineCursorAiderContinueany OpenAI-compatible toolSoulForgeAutohandClineCursorAiderContinueany OpenAI-compatible toolSoulForgeAutohandClineCursorAiderContinueany OpenAI-compatible toolSoulForgeAutohandClineCursorAiderContinueany OpenAI-compatible tool0+
Models
0+
Providers
0×
Usage value
Runs on the open-source LLM Gateway — 100B+ tokens routed · 20K+ GitHub stars
The meter
What you pay vs. what you get
Every plan includes the full 200+ model catalog. The only things that change are your monthly usage allowance and the weekly fair-use cap on premium models.
Lite
For evenings-and-weekends coding
≈ $0.97/day · switch or cancel anytime
Worth 3× what you pay in model usage, metered at provider list rates.
- Model catalog
- 200+ models
- Frontier fair-use
- 12% of credits
- Support
- All 200+ models — Claude, GPT-5, Gemini, GLM, Qwen, …
- DevPass Code, Claude Code, OpenCode, SoulForge & any OpenAI-compatible tool
- Real-time dashboard with per-request cost
7-day first-month guarantee · no lock-in
Pro
For daily development work
≈ $2.63/day · switch or cancel anytime
Worth 3× what you pay in model usage, metered at provider list rates.
- Model catalog
- 200+ models
- Frontier fair-use
- 15% of credits
- Support
- Priority
- Everything in Lite
- Headroom for a full agent session every day
- More frontier fair-use headroom than Lite
- Priority routing on flagship models
7-day first-month guarantee · no lock-in
Max
For all-day, multi-agent workloads
≈ $5.97/day · switch or cancel anytime
Worth 3× what you pay in model usage, metered at provider list rates.
- Model catalog
- 200+ models
- Frontier fair-use
- 18% of credits
- Support
- Front of queue
- Everything in Pro
- Run agents non-stop without watching the meter
- Best frontier-model allowance per dollar
7-day first-month guarantee · no lock-in
Frontier fair-use covers premium models — any model priced at $5+ per million input tokens or $15+ per million output tokens — as a weekly allowance on top of your monthly usage, published right on the card. Every other model draws on your full monthly allowance. No hidden throttling.
First-month guarantee
Try DevPass for a week. If it's not for you, cancel within 7 days of your first purchase and we'll refund your first month minus the usage you consumed at provider rates — one email to contact@llmgateway.io.
No subscription? Pay as you go
The same 200+ 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 triples every dollar.
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 → $87 at provider rates
Same dollars, 3× the metered usage — in whatever editor or agent you already use.
See the full DevPass vs Cursor comparisonPassport 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, SoulForge, and every OpenAI-compatible tool get stamped in with two env vars.
Entries · Visas
PAGE 04
LLM Gateway
DEVPASS
Terminal · Coding · Passport
TAP TO OPEN
LLM Gateway · DevPass
- Bearer
- DevPass Code
- Type
- First-party terminal agent
- Issued by
- LLM Gateway
- Access
- 200+ models · all tiers
P<GTWDEVPASS<CODE<<FIRST<PARTY<AGENT<<<<<<<<<<
LLMGTWY2026<<3X<USAGE<200<MODELS<<<<<<<<<<<<42
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 — with a single ANTHROPIC_MODEL flip.
OpenCode
LLM Gateway is built into OpenCode. Run `opencode`, type `/connect`, paste your DevPass key. No env vars, no config files.
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.
How it works
Up and running in minutes
Pick a plan
Choose Lite, Pro, or Max. Your DevPass key works everywhere — no separate keys per tool.
Plug it into your agent
Two env vars for Claude Code, /connect in OpenCode, /keys in SoulForge. No SDK changes, no code refactor.
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.
Recommended for coding agents
The latest open-weight-lab models — high performance on coding tasks with tool support and prompt caching.
kimi-k3Context: 1.0M
starting from$3.00 in/$15.00 out/M tokens
muse-spark-1.1Context: 1.0M
starting from$1.25 in/$4.25 out/M tokens
glm-5.2Context: 203K
starting from$1.26 in/$3.96 out/M tokens
minimax-m3Context: 524K
starting from$0.30 in/$1.20 out/M tokens
nemotron-3-ultra-550bContext: 262K
starting from$0.50 in/$2.50 out/M tokens
qwen3.7-maxContext: 1.0M
starting from$1.25 in/$3.75 out/M tokens
deepseek-v4-proContext: 1.1M
starting from$0.43 in/$0.87 out/M tokens
mimo-v2.5-proContext: 1.0M
starting from$0.43 in/$0.87 out/M tokens
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: $87 in monthly model usage
- Pro — $79/mo: $237 in monthly model usage
- Max — $179/mo: $537 in monthly model usage
That's roughly 3× the subscription price — effectively model access at a deep discount compared to paying providers directly.
Stop watching your token balance
Pick a plan, set two env vars, get back to building.
First-month guarantee · no lock-in · no cancellation fee