About Grok 4
Grok 4 is xAI's latest reasoning model with a 256k context window. It supports parallel tool calling, structured outputs, and both image and text inputs. Note that reasoning is not exposed, reasoning cannot be disabled, and the reasoning effort cannot be specified. Pricing increases once the total tokens in a given request is greater than 128k tokens. See more details on the [xAI docs](https://docs.x.ai/docs/models/grok-4-0709)
Specifications
- Provider
- xAI
- Context Length
- 256,000 tokens
- Input Types
- image, text
- Output Types
- text
- Category
- Grok
- Added
- 7/9/2025
Benchmark Performance
How Grok 4 compares to its closest rivals across industry benchmarks
30 problems from the 2025 American Invitational Mathematics Examination testing olympiad-level math reasoning
Metric: Accuracy %
#5
Claude-Opus-4.1 (Think)
25.6
Challenging math contest benchmark featuring the most difficult olympiad-level problems
Metric: Accuracy %
#5
Claude-Opus-4.1 (Think)
25.6
Comprehensive comparison of AI models across intelligence, price, speed, and latency
Metric: Intelligence Index
#7
Kimi K2 Thinking
67.0
#9
MiMo-V2-Flash
66.0
#16
MiniMax-M2.1
64.0
Comparison with Grok 3
| Specification | Grok 3 Previous | Grok 4 Current | Change |
|---|---|---|---|
| Context Window | 131K | 256K | |
| Reasoning Support | |||
| Input Types | text | image, text | |
| Output Types | text | text | |
| LMArena Score | 1410 | 1477 | |
| Input Price (per 1M) | $3.00 | $3.00 | |
| Output Price (per 1M) | $15.00 | $15.00 |
Frequently Asked Questions
Common questions about Grok 4