SpaceXAI
Grok 4.6 (high)
Quality Score73.4
Value Score50.1
Reliability65.2
Cache Discount75%
Model specification
- Reasoning
- reasoning
- Input modalities
- text, image
- Output modalities
- text
- Context window
- 500k tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $2.00
- Output
- $6.00
- Cached Input
- $0.500
- Cached Output
- not available
- Cost per task
- $0.837
Capability
- Intelligence
- 60.9
- Coding
- 76.8
- Agentic
- 58.7
- Omniscience
- 30.5
- Correct
- 48.2%
- Blended price
- $1.35
Answer outcomes
Correct 48.2%Incorrect 17.8%Abstained 34.0%
Artificial Analysis benchmarks
- GDPval-AA v2
- 62%
- τ³-Banking
- 51%
- Terminal-Bench v2.1
- 88%
- SciCode
- 54%
- Humanity’s Last Exam
- 43%
- GPQA Diamond
- 95%
- CritPt
- 17%
- AA-Omniscience
- 65%
- AA-LCR
- 75%
Similar models
- Grok 4.6 (xhigh)SpaceXAIQuality Score 71.4Value Score 48.4
- Grok 4.6 (medium)SpaceXAIQuality Score 70.3Value Score 47.5
- Grok 4.5 (high)SpaceXAIQuality Score 69.1Value Score 48.0
- Grok 4.6 (low)SpaceXAIQuality Score 65.1Value Score 43.2
- Grok 4.3 (medium)SpaceXAIQuality Score 48.7Value Score 33.3
- Grok 4.3 (low)SpaceXAIQuality Score 46.7Value Score 32.3