Name: DevPass by LLM Gateway
Brand: LLM Gateway

Question 1

How much usage do I get on each plan?

Accepted Answer

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.

Question 2

How is usage calculated?

Accepted Answer

Usage is metered at each provider's published per-token rate (input, output, and cached tokens). You can see the dollar value of every request in your dashboard in real time.

Question 3

What happens if I hit my monthly limit?

Accepted Answer

Requests pause until your allowance resets at the start of the next billing cycle. Or upgrade to a higher tier at any time: an immediate upgrade charges the new tier's full price, restarts your billing cycle, and grants the new tier's full monthly allowance right away — plus anything left of your current allowance rolls over. Credits only roll over on an immediate upgrade, never at a regular renewal.

Question 4

Can I change plans anytime?

Accepted Answer

Yes. Upgrades can take effect immediately — you're charged the new tier's full price, your billing cycle restarts, and you get the new tier's full allowance right away, plus any unspent credits from the cycle being replaced roll over until your next renewal — or you can schedule the upgrade for your next renewal instead. Downgrades take effect at your next renewal. There's no lock-in and no cancellation fee.

Question 5

Do I need a subscription, or is there pay-as-you-go?

Accepted Answer

Both work. DevPass plans turn every dollar into $3 of model usage. If you'd rather not subscribe, LLM Gateway offers pay-as-you-go: top up credits and pay per token at provider rates with a flat 5% platform fee, or bring your own provider keys for free. Pay-as-you-go organizations can optionally enable full data retention, billed at $0.01 per 1M tokens; DevPass is metadata only and has no retention option.

Question 6

Can my team or company use DevPass?

Accepted Answer

No. DevPass is intended for private, personal use by individual developers — one developer, one account. It can't be purchased or shared as a team or company, and there are no team plans. For teams and companies, use LLM Gateway's pay-as-you-go product instead, and reach out to contact@llmgateway.io for custom solutions and volume discounts.

Question 7

Which tools and SDKs work with DevPass?

Accepted Answer

Anything that speaks the OpenAI or Anthropic API — Claude Code, Empryo, SoulForge, Cursor, Cline, Continue, Aider, the OpenAI and Anthropic SDKs, and more. Set two environment variables and you're in.

Question 8

Are all 200+ models included on every plan?

Accepted Answer

Yes. Every plan includes the full catalog — Claude, GPT-5, Gemini, Llama, Qwen, and the rest. Plans differ in the size of your monthly usage allowance and the weekly fair-use allowance on premium frontier models.

Question 9

Can I pin a specific provider, like on pay-as-you-go?

Accepted Answer

No — DevPass always smart-routes. You request a model by its plain id (e.g. claude-sonnet-5) and the gateway picks the best provider in real time based on uptime, speed, price, and prompt caching — that routing is part of how DevPass stretches every dollar into $3 of usage. Provider-prefixed model ids like openai/gpt-4o aren't available on DevPass; your coding sessions still stick to one provider automatically to keep prompt caches warm. If you need to pin an exact provider or region, use LLM Gateway's pay-as-you-go API on llmgateway.io, which fully supports provider pinning.

Question 10

Are there limits on premium models?

Accepted Answer

Premium models — any model priced at $5+ per million input tokens or $15+ per million output tokens — are subject to a weekly fair-use allowance in addition to your monthly allowance: 12% of your monthly credits on Lite, 15% on Pro, and 18% on Max. Every other model draws on your full monthly allowance. The exact numbers are published on the plan cards — no hidden throttling.

Question 11

What if I hit the weekly premium allowance mid-week?

Accepted Answer

Redeem a Reset Pass: it instantly restores your full weekly premium allowance and starts a fresh 7-day window. A pass removes the weekly limit only — it doesn't add credits, so usage still draws from your monthly allowance. Pro includes 1 pass per billing cycle and Max includes 2; extra passes are a one-time purchase from your dashboard ($9 on Lite, $29 on Pro, $79 on Max). Standard models keep working the whole time, and if you're resetting every week, upgrading a tier is usually the better deal.

Question 12

Does the weekly premium allowance reset when my plan renews?

Accepted Answer

Yes. Every monthly renewal resets everything at once: your monthly credits, your weekly premium allowance (a fresh 7-day window starts at renewal), and your included Reset Passes. Between renewals the window is rolling — when 7 days end, the next window starts with your next premium request, and redeeming a Reset Pass clears the window so the next request starts a fresh one. There's no reset schedule to manage — neither the weekly window nor unused included passes carry into the next cycle. Purchased Reset Passes are separate: they persist until redeemed.

Question 13

Can I get a refund?

Accepted Answer

Yes — DevPass comes with a first-month guarantee. Cancel within 7 days of your first purchase and email contact@llmgateway.io: we'll refund your first month minus the usage you consumed at provider rates. There's no cancellation fee.

Feature	Lite $29/mo	ProPOPULAR $79/mo	Max $179/mo
Usage value (metered at provider rates)	3× what you pay	3× what you pay	3× what you pay
Premium model fair-use ($5+/M input or $15+/M output)	12% of credits	15% of credits	18% of credits
Reset Passes included (instant premium-allowance reset)	Buy anytime · $9	1/month · extras $29	2/month · extras $79
Priority routing on flagship models	Not included	Included	Included
Support	Email	Priority	Front of queue
Headroom for all-day agent runs	Not included	Not included	Included

Flat rate. Every model.
No token math.

Lite

Pro

Max

Where the plans differ

Not sure which plan fits?

Common questions

Still deciding?

Flat rate. Every model.No token math.