Grok 4.7 (Global) pricing, context window and limits
Grok 4.7 (Global) costs $2 per million input tokens and $6 per million output tokens at Amazon Bedrock list price. It accepts up to 500,000 tokens of context and returns up to 500,000 tokens.
- Model id
bedrock/global.xai.grok-4.7 - Snapshot
What does Grok 4.7 (Global) cost?
| Input | $2 |
|---|---|
| Output | $6 |
| Cached input (read) | $0.5 |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can Grok 4.7 (Global) read and write?
| Context window | 500,000 |
|---|---|
| Max output | 500,000 |
What can Grok 4.7 (Global) do?
| Vision (image input) | Yes |
|---|---|
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning | Yes |
| Input | text, image, pdf |
| Output | text |
What does a request to Grok 4.7 (Global) cost?
| A typical request: 1,000 tokens in, 500 out | $0.005 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.026 |
| 1,000 typical requests | $5 |
| 1 million tokens in and 1 million out | $8 |
Input read from the provider's prompt cache costs $0.5 per million tokens instead of $2, 75% less. A request that repeats a 1,000-token prompt from the cache costs $0.0035 instead of $0.005.
Among 199 Amazon Bedrock models with a published price, Grok 4.7 (Global) is the 99th cheapest by input price. Its context window is the 103rd largest of 199. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Grok 4.7 (Global) through DVARA?
Configure the bedrock provider in the DVARA LLM Gateway and send the model id bedrock/global.xai.grok-4.7. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
Which other Amazon Bedrock models are there?
- Grok 4.6 (Global)$2 in · $6 out · 500K context
- Grok 4.6 (US)$2.2 in · $6.6 out · 500K context
- Grok 4.7 (US)$2.2 in · $6.6 out · 500K context
- Grok 4.3$1.25 in · $2.5 out · 1M context
- Grok 4.6$2.2 in · $6.6 out · 500K context
- GLM-5.3 (Global)$1.68 in · $5.28 out · 1M context
- GPT-6.1 Sol (Global)$2 in · $10 out · 1.05M context
- Gemma 3 12B IT$0.09 in · $0.29 out · 131K context
- GPT-6 Sol (Global)$2 in · $10 out · 1.05M context
- Gemma 3 27B IT$0.23 in · $0.38 out · 131K context
- GPT-6 Luna (Global)$0.1 in · $0.5 out · 1.05M context
- Gemma 3 4B IT$0.04 in · $0.08 out · 131K context
Which models from other providers are similar to Grok 4.7 (Global)?
These are the closest in context window and input price, one per provider.
- Grok 4.5xAI Grok · $2 in · $6 out · 500K context
- GPT-5.2OpenAI · $1.75 in · $14 out · 400K context
- Magistral Medium (latest)Mistral AI · $2 in · $5 out · 262K context
- Claude Sonnet 5Anthropic · $2 in · $10 out · 1M context
- Kimi K2.7 Code HighSpeedMoonshot AI · $1.9 in · $8 out · 262K context