AI Desk · AI FingerprintingNew arrival
Why high: an exact fingerprint shared with 2 models that declare the same family, without a second signal of a different kind yet.
SpaceXAI: Grok 4.7 is xAI's model. Its measured tokenizer sits with the Grok group, which is evidence that it builds on the Grok tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against xAI's authorship of the model itself.
| We checked | What we found | Where it came from |
|---|---|---|
| How it counts tokens | Counts every one of the 50 test strings exactly like 2 other models | tk_cb7f8e86 |
| How its API is set up | Set up identically to 1 other listing, field for field | api_81d6ab90 |
| How much it can read and write | Reads up to 500,000 tokens at onceOpenRouter's listing shows 450,000 output tokens, which is 90% of the context window, the figure it carries where the provider declares no maximum. | its own listing |
| Whether it thinks before answering | Always reasons, and cannot be turned off, at xhigh, high, medium, low, high by default | its own listing |
| Who served our requests | xAI | we measured it, 5 October 2026 |
Click a row to open the full comparison.
We sent SpaceXAI: Grok 4.7 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.
Overhead subtracted: 1242 prompt tokens.
Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...
Supported parameters
include_reasoninglogprobsmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstemperaturetool_choicetoolstop_logprobstop_p
defaults: {"temperature":0.7,"top_p":0.95}
