Token metering, unified

Atlas

One ledger for every model

Atlas meters self-hosted Whisper by the word and every other model by the token — under one registry that never runs out of room for the next one.

How it works

Two pricing strategies, one system

Every model in Atlas maps to exactly one strategy. Adding a model never means adding a special case.

Self-hosted Whisper — per word

Transcription cost tracks what the model actually produced: words on the page, not tokens under the hood. Cost = words transcribed × rate for that Whisper variant.

Every other model — per token

Language, vision, and everything else bills on tokens consumed, the native unit those models already report. Cost = tokens used × rate for that model.

Built to extend

No ceiling on models or strategies

The registry holds the models. The strategy decides how they're priced. Neither one is hardcoded against the other.

Add a model

One registry entry: id, strategy, rate. No code change, no redeploy.

Add a strategy

Per-second audio, per-image, per-call — one new strategy module, existing models untouched.

Usage stays flat

The usage ledger only ever stores units consumed and cost — schema never migrates for a new model.

Catalog

Every model, one table

ModelCategoryStrategyRate
Whisper TinySelf-hosted transcriptionPer word1.5 tokens / word
Whisper BaseSelf-hosted transcriptionPer word2.5 tokens / word
Whisper SmallSelf-hosted transcriptionPer word4 tokens / word
Whisper MediumSelf-hosted transcriptionPer word5.5 tokens / word
Whisper Large v3 Turbo Q5_0Self-hosted transcriptionPer word6 tokens / word
Whisper Large v3 TurboSelf-hosted transcriptionPer word7 tokens / word
Whisper Large v3Self-hosted transcriptionPer word9 tokens / word

Meter anything, forever

Atlas doesn't care how many models you add next year. It only cares which strategy they use.

Back to top