SpaceXAI: Grok 4.7 (batch)
by xAItext+image+file->text
Neura Intelligence Index
63.0/ 100
Rank
#132—
Confidence
mediumBenchmarks
4(10% coverage)
Overview
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...
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
Country
🇺🇸US
Release Date
July 9, 20251y
Supported Parameters
include_reasoninglogprobsmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstemperaturetool_choicetoolstop_logprobstop_p
Benchmark Performance
math
| Benchmark | Score | Source |
|---|---|---|
| AIME 2025 | 91.7 | verified |
reasoning
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 87.5 | verified |
| Humanity's Last Exam | 40 | verified |
| ARC-AGI v2 | 15.9 | verified |
Performance Over Time
Pricing
Per 1M tokens
Input$1.60
Output$4.80
Cache read$0.40
Added
September 21, 2026
Last synced 11/7/2026