xAI

SpaceXAI: Grok 4.5

by xAItext+image+file->text4 endpoints
Neura Intelligence Index
85.3/ 100
Rank
#22
Confidence
low
Benchmarks
2(5% coverage)

Overview

Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

Capabilities

Text generation
Image understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
File input
Top-P sampling
Deterministic seed
Log probabilities

Modalities

Input
TextImageFile
Output
Text

Technical Specifications

Context Window
500K tokens
Max Output
450K tokens
Tokenizer
Grok
Uptime (24h)
9969.2%
Country
🇺🇸US
Release Date
July 16, 20262mo

Supported Parameters

include_reasoninglogprobsmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstemperaturetool_choicetoolstop_logprobstop_p

Benchmark Performance

coding

BenchmarkScoreSource
SWE-Bench Pro
64.7
verified

reasoning

BenchmarkScoreSource
GPQA Diamond
93
verified

Performance Over Time

Pricing

Per 1M tokens
Input$2.00
Output$6.00
Cache read$0.30
Added
July 8, 2026
Last synced 9/18/2026