xAI · Model
Grok 4.7 pricing, context window and specs
Grok 4.7 costs $2 per million input tokens and $6 per million output tokens, and reads up to 500,000 tokens per request. By blended price it is the most expensive in xAI's current line-up.
- Input / 1M
- $2
- Output / 1M
- $6
- Cached / 1M
- $0.50
- Context
- 500,000
- Max output
- Not published
- Released
- 2026-09-21
Estimate your cost with Grok 4.7Compare all xAI modelsCount tokens for Grok 4.7
Pricing
Grok 4.7 API pricing
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $2 | $6 |
| Cached input (read) | $0.50 | – |
| Prompts of 200,000+ tokens | $4 | $12 |
Output costs 3.0× the input price, so long replies drive the bill more than long prompts. If your requests share a long fixed prefix, such as a system prompt or tool definitions, caching cuts that part to 25% of the normal input price. Once a single prompt reaches 200,000 tokens, the whole request is billed at the higher long-context rate shown above.
Examples
What Grok 4.7 costs in practice
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot50% cached | 1,500 / 400 | 1,000 | $0.00427 | $130.03 |
| RAG app20% cached | 6,000 / 500 | 500 | $0.0132 | $200.75 |
| Coding agent80% cached | 40,000 / 2,000 | 200 | $0.044 | $267.67 |
| Document summariser | 8,000 / 600 | 300 | $0.0196 | $178.85 |
Change any number in the cost calculator.
Context
Context window
Grok 4.7 accepts up to 500,000 tokens per request, roughly 375,000 English words or 750 pages. That budget is shared between your prompt and the reply, and no separate cap on the reply is published.
Filling the whole window with one prompt costs about $2.00 at list price, so for repeated long-document work, retrieval (sending only the relevant parts) or prompt caching is usually much cheaper.
Features
Capabilities
- Image input
- Yes
- Tool / function calling
- Yes
- Reasoning mode
- Yes
- Prompt caching
- Yes
- Structured output
- Yes
- Open weights
- No
- Accepts
- text, image, file
- Knowledge cutoff
- Not published
As declared by the provider’s API. It shows a feature exists, not how well it works.
xAI
Where Grok 4.7 sits in xAI’s line-up
Ranked by blended price (three parts input to one part output, $3 per 1M for Grok 4.7), it is the most expensive of xAI’s 7 priced models. See every xAI model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Grok 4.7 (this page) | $2 | $6 | 500,000 | 2026-09-21 |
| Grok 4.6 | $2 | $6 | 500,000 | 2026-08-12 |
| Grok 4.5 | $2 | $6 | 500,000 | 2026-07-08 |
| Grok Build 0.1 | $1 | $2 | 256,000 | 2026-05-20 |
| Grok 4.3 | $1.25 | $2.50 | 1,000,000 | 2026-04-30 |
| Grok 4.20 | $1.25 | $2.50 | 2,000,000 | 2026-03-31 |
| Grok 4.20 Multi-Agent | $1.25 | $2.50 | 2,000,000 | 2026-03-31 |
Save
Cheaper alternatives
- DeepSeek V4 Flash Vision ExpDeepSeek89% cheaper
- Qwen3.6 35B A3BQwen88% cheaper
- GLM 4.6VZ.ai85% cheaper
- GPT-5.6 LunaOpenAI85% cheaper
- Muse Glimmer 30BMeta83% cheaper
Current models from major providers, one per provider, that keep image input, tool calling, a reasoning mode, a usable context window and output limit. Compared by blended price.
Compare
Similarly priced models
- Mistral Medium 3.5Mistral$1.50 / $7.50
- Qwen3.8 2.4T A95BQwen$2 / $6
- Gemini 3.5 FlashGoogle$1.50 / $9
- Kimi K3Moonshot AI$0.53 / $12
- GPT-5.1OpenAI$1.25 / $10
Current models from other major providers, closest blended price.
FAQ
Grok 4.7 questions
How much does Grok 4.7 cost?
Grok 4.7 costs $2 per million input tokens and $6 per million output tokens, with cached input at $0.50. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.0054. Use the LLM cost calculator for your own workload.
What is Grok 4.7's context window?
500,000 tokens, about 375,000 English words or 750 printed pages, shared between your prompt and the reply. No separate limit on the reply is published, so the window is the limit.
Does Grok 4.7 support prompt caching and batch requests?
Yes, cached input is billed at $0.50 per million tokens (25% of the normal input price). No batch price is published for it.
What are cheaper alternatives to Grok 4.7?
With the same essentials (image input and tool calling), the cheapest options are DeepSeek V4 Flash Vision Exp (89% cheaper), Qwen3.6 35B A3B (88% cheaper), GLM 4.6V (85% cheaper). Cheaper doesn't mean equivalent, so test them on your own prompts.
Is Grok 4.7 open source?
No, Grok 4.7 is only available through xAI's API and partners; its weights aren't published.