Unlimited Subscriptions

Unlimited subscriptions give you a dedicated model with guaranteed throughput — no budget caps, no token counting. You pick which time blocks you need and subscribe instantly. Your API key gets guaranteed RPM and tok/s during your selected hours.

All endpoints require authentication. Use your management key (mk_):

Authorization: Bearer mk_your_key

---

List available plans

GET /api/pools

Returns all active Unlimited plans.

curl https://api.cheapestinference.com/api/pools \
  -H "Authorization: Bearer mk_your_key"

{
  "success": true,
  "data": [
    {
      "id": "pool_uuid",
      "slug": "minimax-m25",
      "modelId": "MiniMax-M2.5",
      "modelName": "MiniMax M2.5",
      "description": "Dedicated MiniMax M2.5 with unlimited usage.",
      "status": "active",
      "totalSlots": 10,
      "minPricePerDay": "39.00",
      "manualProvisioning": false,
      "annualDiscount": 0.15
    }
  ]
}

Field	Description
status	draft (not listed), funding (accepting pledges), activating (spinning up), active (open for subscriptions), or paused
minPricePerDay	Lowest monthly price across all time blocks (USD, per seat)
manualProvisioning	If true, key is delivered manually (usually within hours, always within 24h)
annualDiscount	Fraction off when billed yearly (0.15 = 15% off). Applied when billingCycle: "year" is passed to subscribe.

---

Plan detail

GET /api/pools/:id

Returns full plan info including all hour slots. :id can be the UUID or slug.

curl https://api.cheapestinference.com/api/pools/minimax-m25 \
  -H "Authorization: Bearer mk_your_key"

{
  "success": true,
  "data": {
    "id": "pool_uuid",
    "slug": "minimax-m25",
    "modelId": "MiniMax-M2.5",
    "status": "active",
    "hourSlots": [
      { "id": "slot_uuid", "hour": 0, "slotIndex": 0, "pricePerDay": "4.88", "status": "available" },
      { "id": "slot_uuid", "hour": 1, "slotIndex": 0, "pricePerDay": "4.88", "status": "available" }
    ]
  }
}

Each hourSlot represents one hour of one seat. Prices are monthly amounts distributed across the 8 hours in a block.

---

Subscribe

POST /api/pools/:id/subscribe

Subscribe using block names. Your card is charged immediately and you receive your API key.

Time blocks

Each day is divided into three fixed UTC blocks:

Block	Hours (UTC)	Region
asia	00:00–07:59	Asia-Pacific
europe	08:00–15:59	Europe / Middle East
americas	16:00–23:59	Americas

Request body

Parameter	Type	Required	Description
blocks	string[]	Yes	One or more: "asia", "europe", "americas"
quantity	integer	No	Seats per block (1–20, default 1)
billingCycle	string	No	"month" (default) or "year" — annual charges upfront with the pool’s annualDiscount applied

Example — one block, monthly

curl -X POST https://api.cheapestinference.com/api/pools/minimax-m25/subscribe \
  -H "Authorization: Bearer mk_your_key" \
  -H "Content-Type: application/json" \
  -d '{"blocks": ["americas"]}'

Example — all blocks, 2 seats, billed annually

curl -X POST https://api.cheapestinference.com/api/pools/minimax-m25/subscribe \
  -H "Authorization: Bearer mk_your_key" \
  -H "Content-Type: application/json" \
  -d '{"blocks": ["asia", "europe", "americas"], "quantity": 2, "billingCycle": "year"}'

Annual amount = monthlyPrice × 12 × (1 − pool.annualDiscount). The discount fraction is returned on the pool detail response (see below). Charges occur upfront; subscription renews yearly until canceled.

Response

{
  "success": true,
  "data": {
    "id": "subscription_uuid",
    "poolId": "pool_uuid",
    "status": "active",
    "monthlyPrice": "39.00",
    "hours": [
      { "hour": 0, "slotIndex": 0, "pricePerDay": "4.88" },
      { "hour": 1, "slotIndex": 0, "pricePerDay": "4.88" }
    ],
    "key": null
  }
}

Note: No API key is created automatically. Use POST /api/keys/subscription to create your key when ready, optionally passing {"subscriptionId": "subscription_uuid"} to target a specific subscription.

Unlimited throughput — no RPM or TPM caps. The only limit is 1 concurrent request per key. Your key is live 24/7 during your subscribed blocks.

If the plan has manual provisioning enabled, status will be pending_key and key will be null. You’ll receive an email when your key is ready.

Pricing

monthlyPrice = sum of prices for all selected slots. Each block has a fixed monthly price. With quantity: 2 and two blocks, you pay 2 × (block_a + block_b).

---

View my subscriptions

GET /api/pools/:id/my-subscriptions

Returns all your active subscriptions for this pool (you can have multiple if you purchased additional blocks).

curl https://api.cheapestinference.com/api/pools/minimax-m25/my-subscriptions \
  -H "Authorization: Bearer mk_your_key"

{
  "success": true,
  "data": [
    {
      "id": "subscription_uuid",
      "status": "active",
      "monthlyPrice": "39.00",
      "billingCycle": "month",
      "cancelAtPeriodEnd": false,
      "currentPeriodEnd": "2026-05-14T00:00:00.000Z",
      "hours": [
        { "hour": 16, "slotIndex": 0, "pricePerDay": "4.88" }
      ],
      "key": {
        "id": "key_uuid",
        "apiKey": "sk_pool_abc123...",
        "isActive": true
      }
    }
  ]
}

Field	Meaning
status	active, pending_key, past_due or canceled
billingCycle	"month" or "year" — chosen at subscribe time
cancelAtPeriodEnd	true when the user has scheduled cancellation; access remains until currentPeriodEnd

status semantics:

status	Meaning
active	Subscription running, key is live
pending_key	Paid, key being set up (manual provisioning)
past_due	Payment failed, key suspended
canceled	Subscription ended

---

Get my keys

GET /api/pools/:id/my-keys

Returns all API keys from all your subscriptions on this pool.

curl https://api.cheapestinference.com/api/pools/minimax-m25/my-keys \
  -H "Authorization: Bearer mk_your_key"

Use any apiKey as Authorization: Bearer on any /v1/* or /anthropic/* inference endpoint.

---

Cancel subscription

DELETE /api/pools/:id/pledge

Cancels your most recent subscription. Schedules cancellation at the end of the current billing period. Your key keeps working until currentPeriodEnd; after that Stripe stops renewing, the key is revoked, and the slots are freed. No refund is issued for unused time.

curl -X DELETE https://api.cheapestinference.com/api/pools/minimax-m25/pledge \
  -H "Authorization: Bearer mk_your_key"

{
  "success": true,
  "data": { "canceled": true }
}

---

How Unlimited works

1. Browse — pick a model and select your time blocks (Asia, Europe, Americas).
2. Subscribe — your card is charged immediately. No API key is created automatically — you create it yourself.
3. Create key — call POST /api/keys/subscription to generate your API key. You can have multiple keys if you have multiple subscriptions.
4. Use — your key gets unlimited throughput during your selected blocks. No budget limits. The only limit is 1 concurrent request per key.
5. Renew — subscriptions recur monthly. Cancel anytime — access continues to the end of the paid period.