--- title: Grok 4.7 is now available on Amazon Bedrock and in Amp description: xAI's Grok 4.7 is now accessible on Amazon Bedrock through cross-region inference profiles (geo and global), supporting a 500K token context window, four... canonical: https://daily.dev/posts/grok-4-7-is-now-available-on-amazon-bedrock-and-in-amp-rmifabfhl twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Grok 4.7 is now available on Amazon Bedrock and in Amp | daily.dev og:description: xAI's Grok 4.7 is now accessible on Amazon Bedrock through cross-region inference profiles (geo and global), supporting a 500K token context window, four... og:url: https://daily.dev/posts/grok-4-7-is-now-available-on-amazon-bedrock-and-in-amp-rmifabfhl og:image: https://api.daily.dev/og/posts/RmIfAbFhl.png og:image:alt: Grok 4.7 is now available on Amazon Bedrock and in Amp og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Grok 4.7 is now available on Amazon Bedrock and in Amp **[Collections](https://daily.dev/sources/collections)** · 2 min read · 0 upvotes · 0 comments ## Summary xAI's Grok 4.7 is now accessible on Amazon Bedrock through cross-region inference profiles (geo and global), supporting a 500K token context window, four reasoning effort levels, and multiple API interfaces including Responses, Chat Completions, InvokeModel, and Converse. It supports Guardrails, prompt caching, structured outputs, and tiered pricing (Standard, Priority, Flex). Benchmarks from Artificial Analysis show gains over Grok 4.6 in intelligence, coding agent performance, and hallucination rate, though output tokens roughly double per task. Grok 4.7 is also now selectable in the Amp coding agent for both the main agent and the oracle mode. ## Content Grok 4.7 is spreading quickly. It has reached xAI's own apps and several third-party platforms. ## In Grok Grok 4.7 is rolling out on the Grok web and mobile apps. According to @testingcatalog, it is now the base model in every mode: Fast, Expert, Build and Heavy. @rohanpaul_ai also noted that it showed up on the web. ## In Amp Amp supports Grok 4.7 as well. @beyang says you pick the agent mode you want to change in settings, then select Grok 4.7 for the main agent, the oracle, or both. ## On Amazon Bedrock Grok 4.7 is available on Amazon Bedrock with a 500K token context window and four reasoning effort levels: low, medium, high and xhigh. It works through the Responses, Chat Completions, InvokeModel and Converse APIs. It is served through two cross-Region inference profiles, Geo (`us.xai.grok-4.7`) and Global (`global.xai.grok-4.7`). Artificial Analysis benchmarks show gains over Grok 4.6 in intelligence, coding agent performance and hallucination rate. The catch is that output tokens roughly double per task, which matters for cost. Bedrock also supports Guardrails, prompt caching, structured outputs, and Standard, Priority and Flex pricing tiers. Authentication works with either Bedrock API keys or IAM-based bearer tokens. ## On Vani.ai Vani.ai now offers Grok 4.7 through Vani Chat's multi-provider interface. It describes the model as aimed at coding, knowledge work and long-running complex tasks, with better verification and longer context than Grok 4.6. The same launch adds two OpenAI models, GPT-6 Sol for multi-step agentic and coding workflows, and GPT-6 Luna, a lighter option for high-volume assistance and document processing. ## Early impressions @nateliason asked whether his bot had moved to 4.7, since it seemed smarter over the past week. He added that he finds himself reaching for Claude and Codex less. That's one anecdote, but it fits the benchmark gains. ## Questions this post answers ### How do I access Grok 4.7 on Amazon Bedrock? Grok 4.7 is available through two cross-region inference profiles: the geo profile us.xai.grok-4.7 and the global profile global.xai.grok-4.7. It supports the Responses, Chat Completions, InvokeModel, and Converse APIs, with authentication via Bedrock API keys or IAM-based bearer tokens, and offers Standard, Priority, and Flex pricing tiers. _daily.dev surfaces integration details like this for engineers wiring new models into their Bedrock stack._ ### What context window and reasoning options does Grok 4.7 support? Grok 4.7 supports a 500K token context window along with four reasoning effort levels: low, medium, high, and xhigh, letting developers trade off latency and cost against reasoning depth for a given task. It also supports Guardrails, prompt caching, and structured outputs on Amazon Bedrock. _Developers tuning reasoning effort against cost can track model capability changes like this on daily.dev._ ### Is Grok 4.7 more expensive to run than Grok 4.6? Yes, output tokens roughly double per task compared to Grok 4.6, according to independent benchmarks from Artificial Analysis, even though the newer model shows improvements in intelligence, coding agent performance, and hallucination rate. Teams should factor this doubled output token usage into cost estimates when upgrading. _Weighing model upgrades against real cost tradeoffs is easier when tracking benchmarks like this on daily.dev._ ## Similar posts on daily.dev - [xAI’s Grok 4.6 is now available in Amazon Bedrock](https://daily.dev/posts/xai-s-grok-4-6-is-now-available-in-amazon-bedrock-fo6p4cpye) · AWS · 1 upvotes · 0 comments --- Tags: [#ai-inference](https://daily.dev/tags/ai-inference), [#grok](https://daily.dev/tags/grok), [#amazon-bedrock](https://daily.dev/tags/amazon-bedrock) [View this post on daily.dev](https://daily.dev/posts/grok-4-7-is-now-available-on-amazon-bedrock-and-in-amp-rmifabfhl) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Grok 4.7 is now available on Amazon Bedrock and in Amp","url":"https://daily.dev/posts/grok-4-7-is-now-available-on-amazon-bedrock-and-in-amp-rmifabfhl","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/grok-4-7-is-now-available-on-amazon-bedrock-and-in-amp-rmifabfhl"},"datePublished":"2026-09-28T22:22:08.701Z","dateModified":"2026-10-02T19:48:52.427Z","description":"xAI's Grok 4.7 is now accessible on Amazon Bedrock through cross-region inference profiles (geo and global), supporting a 500K token context window, four...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/b72564ad8ebec5905a184fc606ef4844?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/b72564ad8ebec5905a184fc606ef4844?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Collections","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Collections","logo":"https://media.daily.dev/image/upload/s--fk_6ycEi--/f_auto,q_auto/v1780996001/logos/collections?_a=BAMAMiWQ0","url":"https://daily.dev/sources/collections"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/grok-4-7-is-now-available-on-amazon-bedrock-and-in-amp-rmifabfhl","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-inference,grok,amazon-bedrock","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collections","item":"https://daily.dev/sources/collections"},{"@type":"ListItem","position":3,"name":"Grok 4.7 is now available on Amazon Bedrock and in Amp"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/grok-4-7-is-now-available-on-amazon-bedrock-and-in-amp-rmifabfhl#faq","mainEntity":[{"@type":"Question","name":"How do I access Grok 4.7 on Amazon Bedrock?","acceptedAnswer":{"@type":"Answer","text":"Grok 4.7 is available through two cross-region inference profiles: the geo profile us.xai.grok-4.7 and the global profile global.xai.grok-4.7. It supports the Responses, Chat Completions, InvokeModel, and Converse APIs, with authentication via Bedrock API keys or IAM-based bearer tokens, and offers Standard, Priority, and Flex pricing tiers. daily.dev surfaces integration details like this for engineers wiring new models into their Bedrock stack."}},{"@type":"Question","name":"What context window and reasoning options does Grok 4.7 support?","acceptedAnswer":{"@type":"Answer","text":"Grok 4.7 supports a 500K token context window along with four reasoning effort levels: low, medium, high, and xhigh, letting developers trade off latency and cost against reasoning depth for a given task. It also supports Guardrails, prompt caching, and structured outputs on Amazon Bedrock. Developers tuning reasoning effort against cost can track model capability changes like this on daily.dev."}},{"@type":"Question","name":"Is Grok 4.7 more expensive to run than Grok 4.6?","acceptedAnswer":{"@type":"Answer","text":"Yes, output tokens roughly double per task compared to Grok 4.6, according to independent benchmarks from Artificial Analysis, even though the newer model shows improvements in intelligence, coding agent performance, and hallucination rate. Teams should factor this doubled output token usage into cost estimates when upgrading. Weighing model upgrades against real cost tradeoffs is easier when tracking benchmarks like this on daily.dev."}}]} ```