Back
FR

Model creator

SpaceXSI

Every SpaceXSI model in the BenchSift catalogue, with its scores, ranks, prices and capabilities as the sources publish them.

View in the catalogue
Models
33
45 configurations, reasoning levels included
Open weights
2
2 of 33 models
Latest release
Nov 10, 2026
SpaceXAI: Grok STT 2.0 · First dated model: Mar 17, 2024
Median price
$2.28
$0.275 to $6 per million tokens, across 12 priced models

Best scores and ranks

The creator's best model on each measure, and its rank among every measured model in the catalogue.

Intelligence

Grok 4.6 (Medium)
42.8Rank 45 of 782 measured models

Coding

Grok 4.6 (High)
75.9Rank 22 of 301 measured models

Math

Grok 4
92.7Rank 16 of 270 measured models

Agentic

Grok 4.6 (High)
52.5Rank 10 of 191 measured models

Output speed

Grok Build 0.1 0616
150 t/sRank 67 of 449 measured models

Lowest price

Grok 4 Fast (Non-reasoning)
$0.275Rank 229 of 740 measured models

OpenRouter ranking

Grok 4.7 (Xhigh)
#44

Capabilities

Number of models that declare each capability. Tool calling and structured outputs come from OpenRouter.
Reasoning15 of 33
Open weights2 of 33
Tool calling6 of 33
Structured outputs13 of 33

Input

  • Text29
  • Image19
  • Files7
  • Audio5

Output

  • Text21
  • Image5
  • Speech5
  • Video4
  • Transcription2

Overview

Model types

  • Text21
  • Audio5
  • Video4
  • Image3

Releases by year

  • 202622
  • 20257
  • 20243

Models

33

Reasoning levels are folded into one entry. The rank is the whole catalogue's: sorting does not change it.

Where these figures come from

Each catalogue model is tied to its creator by the identity Artificial Analysis publishes, or OpenRouter's and Models.dev's for models it does not track. Counts fold the reasoning levels of one model together. Ranks compare each measure with every measured model in the catalogue, configurations included, as model pages do. The price is the published blended price (3 input tokens to 1 output token).

Figures computed by BenchSift from the catalogue: Artificial Analysis, OpenRouter, Models.dev and Hugging Face. A value no model carries is not shown.

Data retrieved on Nov 12, 2026.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy