xAI
SpaceXAI: Grok 4.5
x-ai/grok-4.5
Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.
Input
$2
/ 1M tokens
Output
$6
/ 1M tokens
Context window
500K
tokens
Limits
Context
500,000
tokens
Max output
450,000
90% of the context window
Model facts
Author
xAI
Tokenizer
Grok
Modality
Text + Image + File -> Text
Created
Jul 8, 2026
Reasoning
RequiredDefault HighHighMediumLow
Publication status
Hugging Face: not mappedLicense: not publishedParameter count: not published
Modalities
Input · TextInput · ImageInput · FileOutput · Text
Generation controls
Include reasoningLogprobsMax tokensReasoningReasoning effortResponse formatSeedStructured outputsTemperatureTool choiceToolsTop logprobsTop p
Capability scores
41.2
Agentic index
Better than 73% of models compared
72.4
Coding index
Better than 82% of models compared
38.8
Intelligence index
Better than 81% of models compared
Agent tasks
Category performance
Android apps
Top 21%1249 Elo
63.9% win
Full-stack apps
Top 19%1249 Elo
60.7% win
Godot games
Top 34%1229 Elo
58.2% win
Agentic games
Top 25%1235 Elo
55.9% win
Slide decks
Top 45%1230 Elo
53.9% win
Web apps
Top 38%1208 Elo
53.5% win
Mobile apps
Top 30%1216 Elo
52.9% win
HTML slides
Top 31%1204 Elo
52.5% win
Creative tasks
Category performance
ASCII art
Top 32%1255 Elo
54.1% win
Websites
Top 22%1282 Elo
52.4% win
UI components
Top 25%1279 Elo
51.4% win
Code
Top 25%1277 Elo
50.9% win
3D
Top 29%1259 Elo
50.2% win
Data visualization
Top 25%1268 Elo
49.8% win
Games
Top 29%1264 Elo
49.2% win
SVG
Top 30%1216 Elo
48.3% win