Grok 4.7
xAI's frontier model for long-running agents, coding, knowledge work, and visual projects.
- Capability
- 156.4ECI · #37 of 158
- Input
- $2.00per 1M tokens
- Output
- $6.00per 1M tokens
- Context
- 500K500K max output
What it costs
- Input
- $2.00per million tokens
- Output
- $6.00per million tokens
- Cached input
- $0.50per million tokens
- Over 200K tokens
- $4.00 / $12.00input / output per million
- Blended (3:1)
- $3.00pricier than 76% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $7.00 |
| Team assistant25M input + 5M output tokens | $80.00 |
| Production app250M input + 50M output tokens | $800.00 |
Official xAI API price, as listed on models.dev.
Independent benchmarks
#37 of 158 scored models
The shaded band is Epoch AI’s confidence range (154.5–158.5); the tick marks the median scored model.
Scores from Epoch AI, run independently of xAI.
The details
- Lab
- xAI
- Released
- Sep 21, 2026
- Knowledge cutoff
- May 2026
- Context window
- 500,000 tokens
- Max output
- 500,000 tokens
- Inputs
- Text, Images, PDFs
- Output
- Text
- Reasoning
- Adjustable effort low · medium · high · xhigh
- Tool calling
- Yes
- Structured output
- Yes
- Weights
- Proprietary
- API model ID
grok-4.7on xAI- Availability
- 35 API providerslisted on models.dev
What xAI claims
Published by the lab at launch. Settings vary, so compare these only with care.
| Benchmark | Score | Setting | Source |
|---|---|---|---|
| CursorBench v4.0 | 46.3 | xhigh effort | Source |
| DeepSWE v1.1 | 71 | high effort | Source |
| EEBench | 64 | xhigh effort | Source |
| AA-Briefcase v1.1 | 1657 Elo | xhigh effort | Source |
| Terminal-Bench v4.0 | 37.6 | xhigh effort | Source |
| Harvey Legal Agent Benchmark | 19.6 | xhigh effort | Source |
| HealthBench | 56.7 | xhigh effort; professional | Source |
| GDPval | 1695 Elo | xhigh effort | Source |
More from xAI
About Grok 4.7
How much does Grok 4.7 cost?
Grok 4.7 costs $2.00 input / $6.00 output per million tokens (official xAI API price). Cached input is $0.50 per million tokens. Requests over 200K tokens are billed at $4.00 input / $12.00 output. At a 3:1 input-to-output mix that is $3.00 per million tokens, more expensive than 76% of the 469 priced models we track.
What is the context window of Grok 4.7?
Grok 4.7 accepts up to 500,000 tokens per request and can write up to 500,000 tokens in one response.
How good is Grok 4.7?
Epoch AI gives Grok 4.7 a Capabilities Index score of 156.4 (likely range 154.5–158.5), ranking it #37 of 158 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 92.7%, FrontierMath Tiers 1–3 53.0%, OTIS Mock AIME 2024–2025 98.1%, SimpleQA Verified 56.0%.
Is Grok 4.7 open source?
No. Grok 4.7 is proprietary; you use it through xAI’s API or partner platforms.
What inputs does Grok 4.7 support?
Grok 4.7 accepts text, images and PDFs and replies in text. It is a reasoning model with low, medium, high and xhigh effort settings, supports tool calling and can return structured JSON output.
When was Grok 4.7 released?
xAI released Grok 4.7 on Sep 21, 2026. Its training data runs to May 2026.
What are the best alternatives to Grok 4.7?
The closest current models from other labs on capability, price and release date are Qwen3.8 Max 0902 (Alibaba (Qwen), ECI 156.0, $2.00 / $6.00), GLM-5.3 (Z.ai (Zhipu), ECI 157.1, $1.40 / $4.40), Claude Sonnet 5 (Anthropic, ECI 156.9, $2.00 / $10.00) and Muse Spark Open (Meta, ECI 155.5, $1.25 / $4.25).