Overview
Serverless inference is priced per token. For how Standard, Priority, and Fast serving paths work and how to select one, see Serverless Serving Paths. Every text or vision request is billed across three dimensions:- Input tokens — what you send to the model.
- Cached input tokens — input tokens served from prompt cache, priced lower.
- Output tokens — what the model generates.
How pricing works
- Prices below are per 1 million tokens in US dollars.
- Batch inference is billed at 50% of serverless pricing on both input and output. See Batch inference.
Text and vision models
Per-model pricing for headline models. Fast variants appear as adjacent rows. In each Standard or Priority cell, prices are input / cached input / output (USD per 1M tokens), in that order.
— in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability.
Other base models — by size and architecture
For any text or vision model not listed individually, pricing is set by parameter count and architecture. These size-based prices apply uniformly to input and output (no separate cached-input rate):Embeddings
Embeddings are billed per 1M input tokens.Notes
- For account-level controls (spend tiers, monthly budget, on-demand GPU quotas), see Account quotas.