Deploy

Pricing

Prices per model, what is and is not billed, and worked examples.

The hosted Decision API is priced per million input tokens, with output free, paid from prepaid credit in pounds. There is no subscription and no minimum spend.

Prices

ModelLiveBatchList price unchanged since
Myles-G 12B
myles-g-12b
£0.0015 per million input tokens£0.00075 per million input tokens14 October 2026
Myles-G 31B
myles-g-31b
£0.005 per million input tokens£0.0025 per million input tokens19 October 2026

Output tokens are free on every model. Prices exclude VAT; UK VAT is added at checkout. The Batch API answers within 24 hours at half the live price.

What you pay for

  • Input tokens of answered requests. The response's usage.input_tokens is exactly what is billed. It covers the state, the questions and their options, and any images (see Images: billing).
  • Not billed: output tokens; requests that end in an error, including timeouts and refused requests; GET /v1/models and GET /health.
  • Batches: each answered line at the batch price. If you cancel a batch, the lines already answered are billed and the rest are not.

Worked examples

WorkloadMyles-G 12BMyles-G 31B
One typical decision (about 700 input tokens)£0.00000105£0.0000035
A million typical decisions, liveabout £1.05about £3.50
A million typical decisions, batchabout £0.53about £1.75

Shorter states cost less: leave out signatures, footers and quoted history (see Writing the state). Several questions about the same situation in one request share the state's tokens.

Paying

  • Buy prepaid credit in the console, from £5 by card, with optional automatic top-up and low-balance alerts.
  • Credit never expires.
  • Keys work while the account has credit. When it runs out, every key on the account pauses until you top it up.
  • Invoices and receipts come with each payment. Usage is shown per key, workspace and model in the console.

Price changes

A list price on this page holds for every request until a new price is published here, with its date. Credit you have already bought is spent at the price in force when each request is answered.

On your own hardware

Self-hosted Myles is licensed per deployment rather than per token. See Licensing and pricing and On your own hardware.