Primary use stated or inferred cautiously from official documentation.
X
XAI / grok-4.6
Grok 4.6
Coding, research, and professional tool-based workflows.
01 / SUMMARY
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
02 / TECHNICAL SHEET
Limits and integration
| API ID | grok-4.6 |
|---|---|
| Model type | Text and reasoning |
| Access model | Paid proprietary |
| License | Proprietary |
| Deployment | Hosted API |
| Release | 12 AUG 2026 |
| Knowledge cutoff | 1 FEB 2026 |
| Entrance | Text · Image |
| Exit | Text |
| Context window | 500.000 tokens |
| maximum output | No published text limit |
| Reasoning | low, medium, high, and xhigh effort |
| Published tools | Features · Web search · Search on X · Code execution |
| Structured Outings | Supported |
| Batch processing | Not compatible |
| Prompt cache | Supported |
| Fine-tuning | Not published |
| Verified platforms | xAI API · Grok Build · Cursor |
Coding, research, and professional tool-based workflows.
Execution conditions vary across benchmarks; do not compare the number alone.
03 / CAPABILITIES
What it can do
Orientation
Coding, research, and professional tool-based workflows.
Context
500.000 tokens · No published text limit
Tools and integration
Features · Web search · Search on X · Code execution
Access
xAI API · Grok Build · Cursor
Input modalities
TextImage
04 / PRICES
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | 2,00 USD / 1 M tokens | Standard API rate |
| Cached input | 0.50 USD / 1 M tokens | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | 6,00 USD / 1 M tokens | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Input and output pricing doubles above 200,000 tokens.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
05 / EVALUATIONS
How to read the results
“
A public benchmark provides guidance, but does not replace an evaluation with your data, tools, budget, and error tolerance.
| Benchmark | Result | Metric | Source |
|---|---|---|---|
| CursorBench 3.2 | 69,9 % | Accuracy | View source ↗ |
| DeepSWE v1.1 | 65,9 % | Resolved | View source ↗ |
| Terminal-Bench 3.0 | 26,0 % | Accuracy | View source ↗ |
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
06 / VERSIONS
Chronology
Grok 4.6
Version added to Inferama's verified catalog.
ANALYSIS
Related analysis
07 / SOURCES