AI Desk · AI FingerprintingWithdrawn *
| We checked | What we found | Where it came from |
|---|---|---|
| How it counts tokens | Not measured yet | we measured it |
| How its API is set up | Set up identically to 1 other listing, field for field | api_20ca7341 |
| How much it can read and write | Reads up to 260,000 tokens at once, writes up to 65,536 | its own listing |
| Whether it thinks before answering | Reasons when asked to, at high, medium, low, none, medium by default | its own listing |
| Who served our requests | Inception | we measured it, 3 September 2026 |
Click a row to open the full comparison.
We sent Inception: Mercury 2.5 Preview fifty short pieces of text and recorded what each one cost it in tokens. The bars below are those costs. Two models built on the same tokenizer produce the same bars; a model built on a different one produces a different set, which is what makes this a fingerprint.
An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 11 prompt tokens.
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...
Supported parameters
include_reasoningmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstemperaturetool_choicetools
defaults: {}
* Inception: Mercury 2.5 Preview no longer appears in the OpenRouter catalogue, first absent from the snapshot of 16 September 2026. The record stays because the measurements above were real when they were taken and this address has been published.
