AI Inference · Pricing
Docs / AI Inference

Pricing

Per-token and per-unit inference pricing, billed from your prepaid credit balance.

Using a model in the Playground is billed per token for text models and per unit (image or minute) for media models, drawn from your prepaid credit balance. Prices below are in USD.

Model pricing

ModelClassInput /1MOutput /1M
Frontier chat modelFrontier chat$0.88$0.88
Reasoning modelReasoning$0.80$0.80
Frontier chat model (alt.)Frontier chat$0.80$0.80
Fast & cheap chat modelFast & cheap$0.10$0.10
Fast & cheap chat model (alt.)Fast & cheap$0.10$0.10
Image generation modelImage generation$0.04 / image
Audio transcription modelAudio transcription$0.0030 / min
Embeddings modelEmbeddings$0.01

Every Playground result shows the tokens (or units) it used, so you can see roughly what a chat reply, embedding, image, or transcript cost as you go.

Billing
Inference is billed per-token / per-unit from your prepaid credit balance. Top up credits before you run out to avoid interruptions.