Ellipsis uses prepaid credits. Model usage and sandbox compute are paid from your balance.

## What is charged

| Models paid by | Tokens | CPU and memory: personal | CPU and memory: organization |
| --- | --- | --- | --- |
| Ellipsis credits | The model's rate, below | Free | At cost |
| Your Claude subscription | $0 to Ellipsis | Free | At cost |
| Your Codex subscription | $0 to Ellipsis | Free | At cost |

A [subscription](/docs/models#use-your-subscription) covers sessions you start yourself, on personal and organization accounts: from the dashboard, the CLI, the API with your own token, or a mention from a GitHub, Slack, or Linear account linked to your GitHub account. Scheduled and event-triggered agents, sessions started with an API key, and sessions an agent starts use credits.

Organization compute costs $0.141912 per CPU core-hour and $0.024192 per GiB-hour of memory, for the resources allocated while a sandbox runs, including while it waits for your next message.

## Model pricing

Prices in USD per 1 million tokens, for personal and organization accounts.

| Model | Input | Cached input | Output |
| --- | --- | --- | --- |
| Claude Fable 5.1 | $10.00 | $0.25 | $50.00 |
| Claude Opus 5.5 | $4.00 | $0.20 | $20.00 |
| Claude Sonnet 5.5 | $2.00 | $0.20 | $10.00 |
| Claude Haiku 5.5 | $0.10 | $0.01 | $0.50 |
| GPT-6.1 Sol | $2.00 | $0.10 | $10.00 |
| GPT-6 Astra | $10.00 | $1.00 | $50.00 |
| GPT-6 Sol | $2.00 | $0.20 | $10.00 |
| GPT-6 Luna | $0.10 | $0.01 | $0.50 |
| GPT-5.6 Sol | $2.00 | $0.20 | $10.00 |

Cache writes cost 1.25× input for Claude (5-minute) and GPT, or 2× input for Claude (1-hour). A GPT-6 or GPT-6.1 request with more than 272K input tokens, cache reads and writes included, costs 2× input and 1.5× output for the whole request. A Claude Haiku 5.5 request with more than 100K input tokens, cache reads and writes included, costs 5× for the whole request.

## Buy credits

Use **Billing > Credits** to purchase credits. A 10% platform fee applies to credit purchases before discounts, not to individual sessions.

Credits do not expire.

## Automatic recharge

Configure a balance threshold and recharge amount under **Billing > Credits**. A saved payment method alone does not enable automatic recharge.

Paid requests stop when the available balance or an applicable [spend limit](/docs/organization#spend-limits) is exhausted.

## Read usage

**Billing > Usage** shows model and compute usage separately, and each session shows its own cost.

The usage API groups usage by UTC calendar month. For sessions paid by a subscription, it shows what the tokens would have cost; you aren't charged for them.