Grok 4.7
Grok 4.7 is the flagship model on the xAI API, released September 21, 2026 for coding, agentic tasks and knowledge work. It accepts text and images within a 500K-token context window and offers reasoning effort from low to xhigh.
Specifications
- Context window
- 500Kabout 375,000 words, or 750 pages
- Max output
- Not published
- Input price
- $2per 1M tokens
- Output price
- $6per 1M tokens
- Cached input
- $0.50per 1M tokens
- Weights
- ClosedProprietary
- Parameters
- Undisclosed
- Input types
- Text, Images
- Output types
- Text
- Reasoning mode
- Yes
- Tool calling
- Yes
- Released
- Sep 21, 2026Current
Rates for prompts under 200K tokens; at 200K or more, all tokens cost $4 input, $1 cached and $12 output. US regional endpoint adds 10%; Priority processing 2x. max_output is null because xAI states no fixed text output limit.
What it costs in practice
| Workload | Monthly cost at list price |
|---|---|
| Support chatbot30,000 conversations a month, 2,000 input and 400 output tokens each | $192 |
| Document summaries2,000 documents a month, 12,000 input and 800 output tokens each | $58 |
| Coding agent1,000 tasks a month, 60,000 input and 6,000 output tokens each | $156 |
Standard rates, no caching or batch discounts. Run your own numbers.
Strengths
- $2 input and $6 output per million tokens below 200K tokens
- Built-in web search, X search and code execution tools
- Reasoning effort from low to xhigh
Trade-offs to weigh
- Rates double for prompts of 200K tokens or more
- No Batch API support; the faster Grok 4.7 Fast variant is limited to Cursor and Grok Build
Where it fits
xAI positions Grok 4.7 for:
Where you can use it
- API
- OpenRouter
- Cursor
Alternatives to consider
| Model | Tier | Context | Input / output per 1M | |
|---|---|---|---|---|
| Qwen3.8-MaxAlibaba (Qwen) | Frontier | 1M | $2 / $6 | Compare |
| Mistral Large 4Mistral AI | Frontier | 1M | $1.36 / $4.18 | Compare |
| Qwen3.8-2.4T-A95BAlibaba (Qwen) | Frontier | 256K | $2 / $6 | Compare |
| Gemini 3.1 ProGoogle | Frontier | 1M | $2 / $12 | Compare |
Frequently asked questions
How much does Grok 4.7 cost?
Grok 4.7 lists at $2 per million input tokens and $6 per million output tokens, with cached input at $0.50 (checked October 10, 2026). Rates for prompts under 200K tokens; at 200K or more, all tokens cost $4 input, $1 cached and $12 output. US regional endpoint adds 10%; Priority processing 2x. max_output is null because xAI states no fixed text output limit. Confirm current rates on the provider's pricing page before you commit.
What is the context window of Grok 4.7?
Grok 4.7 accepts up to 500,000 tokens of context (about 375,000 words, or 750 pages). Long prompts cost more and can be slower, so most apps send only what the task needs.
Is Grok 4.7 open source?
No. Grok 4.7 is a proprietary model from xAI; its weights aren't published. You can use it through the xAI API and through OpenRouter, Cursor.
What is Grok 4.7 best for?
xAI positions Grok 4.7 for coding, agents, reasoning, research. It accepts text, images as input, has a reasoning (thinking) mode and supports tool calling. Test it on a sample of your own tasks before you choose it for production.
Sources
- docs.x.ai/developers/models/grok-4.7
- docs.x.ai/developers/pricing
- docs.x.ai/docs/models
- docs.x.ai/docs/models/grok-4.7
- docs.x.ai/developers/grok-4-7
- docs.x.ai/developers/release-notes
- x.ai/news/grok-4-7
- openrouter.ai/x-ai/grok-4.7
Facts checked against these pages on October 10, 2026. Spot an error? Tell us.
Still choosing a model?
Send us your use case and constraints. We'll come back with a shortlist and an evaluation plan you can run on your own data.
- Free and vendor-neutral: no model provider pays for placement.
- Your details go only to partners you agree to.