AWS Bedrock

AWS Bedrock: Grok 4.6 (Bedrock)

stable

Grok 4.6 (Bedrock) is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

xai.grok-4.6grokreleased Aug 12, 2026
Context
500K
tokens
Max output
500K
tokens
Input
$2.20
per 1M
Output
$6.60
per 1M

Activity

Daily period usage
Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Providers

ProviderContextInput /MOutput /M

Pricing

ItemPriceUnit
Input$2.20per 1M tokens
Output$6.60per 1M tokens
Cache read$0.55per 1M tokens

Performance

Reliability

Compare

Compare usage and performance
Place this model beside up to three other catalog models.

Capabilities

Capabilities
Modalities
Input
Output
Details
Model ID
xai.grok-4.6
Family
grok
Status
stable
Knowledge
Feb 1, 2026
Released
Aug 12, 2026
Gateway Config
API
2024-01-01
Auth
AWS_REGION
Discovery
static
Provider type
static

Quick Start

index.ts
import Everstack from "@everstack/node";const client = new Everstack({  apiKey: process.env.EVERSTACK_API_KEY!,  baseUrl: "https://{instance}.{region}.everstack.ai",});const completion = await client.chat.completions.create({  model: "@aws-bedrock/xai.grok-4.6",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL
https://bedrock-runtime.{region}.amazonaws.com
Chat completions
https://bedrock-runtime.{region}.amazonaws.com/chat/completions
Model
xai.grok-4.6
Auth env
AWS_REGION

Grok 4.6 (Bedrock) FAQ

How much does the Grok 4.6 (Bedrock) API cost?

Through AWS Bedrock, Grok 4.6 (Bedrock) costs $2.20 per 1M input tokens and $6.60 per 1M output tokens.

What is the context window of Grok 4.6 (Bedrock)?

Grok 4.6 (Bedrock) accepts up to 500K tokens of context and returns up to 500K output tokens on AWS Bedrock.

What can Grok 4.6 (Bedrock) do?

Grok 4.6 (Bedrock) supports chat, function calling, image input and reasoning. It accepts text and image input.

How do I call Grok 4.6 (Bedrock) through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @aws-bedrock/xai.grok-4.6. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.