API pricing

# Inception API pricing

> Inception API prices run from $0.04 per million input tokens (Mercury 2.5) to $0.25 (Mercury 2). Its highest-ranked model, Mercury 2, costs $0.25 input and $0.75 output per million tokens.
- Canonical page: https://noometry.com/llm-pricing/inception
- Last updated: 2026-10-10
- Title: Inception API Pricing (October 2026): Every Model per 1M Tokens

Inception API prices run from $0.04 per million input tokens (Mercury 2.5) to $0.25 (Mercury 2). Its highest-ranked model, Mercury 2, costs $0.25 input and $0.75 output per million tokens.

Last verified October 10, 2026

API prices per million tokens
|  |  |  | Cached input |  |  |  |
| --- | --- | --- | --- | --- | --- | --- |
| [Mercury 2.5](https://noometry.com/models/mercury-2-5) | $0.04 | $0.15 | $0.004 | **$0.0675** | 260K | 33.5 |
| [Mercury 2](https://noometry.com/models/mercury-2) | $0.25 | $0.75 | $0.025 | **$0.38** | 128K | 39.1 |
| [Mercury Edit 2](https://noometry.com/models/mercury-edit-2) | $0.25 | $0.75 | $0.025 | **$0.38** | 32K | — |

## Prices on other platforms

The same models are often sold through clouds and resellers at different rates.

| Model | Route | Input | Output | Checked |
| --- | --- | --- | --- | --- |
| [Mercury 2](https://noometry.com/models/mercury-2) | inception | $0.25 | $0.75 | 2026-10-10 |
|  | openrouter | $0.25 | $0.75 | 2026-10-10 |
| [Mercury 2.5](https://noometry.com/models/mercury-2-5) | inception | $0.04 | $0.15 | 2026-10-10 |
|  | openrouter | $0.04 | $0.15 | 2026-10-10 |
| [Mercury Edit 2](https://noometry.com/models/mercury-edit-2) | inception | $0.25 | $0.75 | 2026-10-10 |

## Frequently asked questions

### How much does the Inception API cost?

Inception API prices run from $0.04 per million input tokens (Mercury 2.5) to $0.25 (Mercury 2). Its highest-ranked model, Mercury 2, costs $0.25 input and $0.75 output per million tokens.

### Does Inception discount cached input?

Yes. Cached input is billed at a lower rate on 3 of the 3 priced models; the cached rate is listed next to each model.