llm11

Credits. No subscription.

You pay what the provider charges, plus 5% when you buy credits. That is the entire price list.

Buy credits

5% fee, once, at purchase

$5

of credit

$5.25 charged

($0.25 fee)

$25

of credit

$26.25 charged

($1.25 fee)

$100

of credit

$105.00 charged

($5.00 fee)

$500

of credit

$525.00 charged

($25.00 fee)

A $25 top-up costs $26.25: $25.00 lands on your balance and $1.25 is the fee. Everything after that debits at exactly what the model, the check and the triage call cost.

Start free, $2.00 of credit

What a credit buys

Model prices, live from the catalogue llm11 routes against. The gap between the ends of a pack is what routing is for, and the receipt on every request tells you which end you landed on.

  1. llm11-fast

    $0.022 to $0.475, 8 models

    mistral-nemoqwen3-coder

  2. llm11-balanced

    $0.536 to $4.81, 8 models

    qwen3.5-27bgpt-5.2

  3. llm11-smart

    $5.63 to $263, 8 models

    gpt-5.4o1-pro

$0.022per million tokens, log scale$263

352 priced models reachable. Rates are blended 3:1 toward prompt tokens and read live from the catalogue the router ranks on, so they move when the providers move.

One request, both ends

A 1,500 token prompt with a 400 token answer, priced on the floor and the ceiling of llm11-balanced right now.

qwen3.5-27b
$0.000917
gpt-5.2
$0.008225

Both figures come from the same per-token rates the receipt uses. Neither is what you will pay on any given request, because that depends on which model triage picks and whether the answer needed checking. It is the range you are choosing inside.

Three packs, or your own list

llm11-fast

The cheapest end of the catalogue. Best for high-volume, low-stakes traffic.

llm11-balanced

A working mix of cheap and capable models. The sane default.

llm11-smart

The most capable models available, priced at whatever that costs.

Pick a pack per project in settings, or send model or llm11_models per request. See the quickstart.

Common questions

Is there a subscription?
No. You buy credits, you spend them, and you buy more when you run out. There is no monthly fee, no seat count, and no feature you have to upgrade to unlock.
Do you mark up any model?
No. Every token debits your balance at the exact figure the provider reported for that call. The only revenue in llm11 is the 5% fee on buying credits in the first place. A layer that profits on the spread has a reason to route you upward, so we removed the reason.
What is a credit?
One US cent of upstream spend. Balances are held to six decimal places, because a real request often costs a fraction of a cent and rounding to the nearest cent would overcharge by orders of magnitude.
What happens when I run out?
Requests stop with a 402 and a clear message. There is no overdraft and no invoice arriving later.
Do you store my prompts?
No, unless you switch retention on for a specific project and set a window. Receipts hold metadata only.
Can I self-host?
Not today. It is on the roadmap for teams who cannot route traffic through a third party at all, and until it exists we would rather say no than imply a timeline.

The retention answer is spelled out field by field on the privacy page.

Pricing is also served as data at /pricing.json, from the same constants this page renders from. llm11 charges the 5% purchase fee and nothing else.