Inference Pricing

Credits for usage, dedicated plans for scale

Prepaid credits are one-time purchases. Dedicated plans support monthly or yearly billing with a 20% discount on yearly contracts.

Custom Inference Top-Ups

Choose any USD amount in the dashboard. One credit equals $0.01 USD and auto top-up uses the same custom amount model.

Top up exactly what you need

Minimum $5.00, maximum $10,000.00. Save a card once to let LLMBase refill your balance automatically when it drops below your threshold.

Open balance dashboard

Managed / Dedicated Inference

Reserved capacity plans for production workloads.

Dedicated Small

Entry dedicated deployment

$299

/month

Billed monthly

Start monthly plan

Dedicated Medium

Higher throughput and concurrency

$899

/month

Billed monthly

Start monthly plan

Dedicated Large

Maximum dedicated capacity

$2,499

/month

Billed monthly

Start monthly plan

Note: yearly dedicated plans are annual contracts with sales-assisted onboarding.

← Back to chat pricing
Customer Support