Checking the Billing Classification of Grok 4.6 on Bedrock in Cost Explorer
This page has been translated by machine translation. View original
Introduction
On August 19, 2026, Amazon Bedrock added support for SpaceXAI's Grok 4.6.
Amazon Bedrock now supports SpaceXAI Grok 4.6, a frontier model built for coding, agentic tasks, and knowledge work, with US Geo and Global cross-Region inference.
The US Geo inference profile—us.xai.grok-4.6—routes requests only within the US geography, so you can scale while keeping data processed within the United States to meet data residency requirements.
The inference profile IDs are us.xai.grok-4.6 for US Geo and global.xai.grok-4.6 for Global.
SpaceXAI states that Grok 4.6 rivals high-end models on multiple benchmarks related to agentic coding and knowledge work.
Grok 4.6 achieves frontier intelligence across several agentic coding and knowledge work benchmarks. It matches GPT-5.6 Sol on the Artificial Analysis Intelligence Index, which is a composite score of nine benchmarks.
IAM authentication on Bedrock, invocation via bedrock-mantle, and a price comparison are covered in the following article.
In this article, I checked which service and which billing entity the usage charges for Grok 4.6 are classified under in Cost Explorer. Using the same dimensions, I also checked how charges are classified when calling Claude and OpenAI GPT via Bedrock, and whether they are offset by AWS credits.
What I Verified
The dimensions used are SERVICE, USAGE_TYPE, BILLING_ENTITY, and RECORD_TYPE.
Service Classification
In a working account with no credits, I retrieved the services that incurred costs from January 1, 2026 to September 1, 2026 (the values of the SERVICE dimension) and extracted only the Bedrock-related ones.
aws ce get-dimension-values \
--time-period Start=2026-01-01,End=2026-09-02 \
--dimension SERVICE \
| jq -r '.DimensionValues[].Value' | grep -E 'Bedrock'
Amazon Bedrock
Amazon Bedrock AgentCore
Claude 3 Haiku (Amazon Bedrock Edition)
Claude 3.5 Haiku (Amazon Bedrock Edition)
Claude 3.5 Sonnet v2 (Amazon Bedrock Edition)
Claude Fable 5 (Amazon Bedrock Edition)
Claude Haiku 4.5 (Amazon Bedrock Edition)
Claude Opus 4.7 (Amazon Bedrock Edition)
Claude Opus 4.8 (Amazon Bedrock Edition)
Claude Opus 5 (Amazon Bedrock Edition)
Claude Sonnet 4.5 (Amazon Bedrock Edition)
Claude Sonnet 4.6 (Amazon Bedrock Edition)
Claude Sonnet 5 (Amazon Bedrock Edition)
OpenAI GPT-5.4 (Amazon Bedrock Edition)
OpenAI GPT-5.5 (Amazon Bedrock Edition)
OpenAI GPT-5.6 Luna (Amazon Bedrock Edition)
OpenAI GPT-5.6 Sol (Amazon Bedrock Edition)
OpenAI GPT-5.6 Terra (Amazon Bedrock Edition)
Claude and OpenAI GPT appeared as independent services for each model, with "(Amazon Bedrock Edition)" appended. On the other hand, among the SERVICE values that include Bedrock in their name, there is no entry for Grok. Grok costs are included in Amazon Bedrock. In the next section, I check its USAGE_TYPE.
USAGE_TYPE
I narrowed SERVICE down to Amazon Bedrock, aggregated by USAGE_TYPE, and extracted only the values for Grok, gpt-oss, and Gemma 4.
aws ce get-cost-and-usage \
--time-period Start=2026-01-01,End=2026-09-02 \
--granularity MONTHLY --metrics UnblendedCost \
--filter '{"Dimensions":{"Key":"SERVICE","Values":["Amazon Bedrock"]}}' \
--group-by '[{"Type":"DIMENSION","Key":"USAGE_TYPE"}]' \
| jq -r '[.ResultsByTime[].Groups[].Keys[0]]|unique|.[]' \
| grep -E 'grok|gpt-oss-120b|gemma-4-31b'
APN1-xai.grok-4.6-mantle-input-tokens-global-standard
APN1-xai.grok-4.6-mantle-output-tokens-global-standard
USE1-google.gemma-4-31b-mantle-input-tokens-standard
USE1-google.gemma-4-31b-mantle-output-tokens-standard
USE1-openai.gpt-oss-120b-mantle-input-tokens-standard
USE1-openai.gpt-oss-120b-mantle-output-tokens-standard
USE1-xai.grok-4.3-mantle-input-tokens-standard
USE1-xai.grok-4.3-mantle-output-tokens-standard
USE1-xai.grok-4.6-mantle-input-tokens-standard
USE1-xai.grok-4.6-mantle-output-tokens-standard
USE2-gpt-oss-120b-input-tokens
USE2-gpt-oss-120b-output-tokens
USE2-openai.gpt-oss-120b-mantle-input-tokens-standard
USE2-openai.gpt-oss-120b-mantle-output-tokens-standard
USW2-google.gemma-4-31b-mantle-input-tokens-standard
USW2-google.gemma-4-31b-mantle-output-tokens-standard
USW2-openai.gpt-oss-120b-mantle-input-tokens-standard
USW2-openai.gpt-oss-120b-mantle-output-tokens-standard
USW2-xai.grok-4.3-mantle-cache-read-tokens-standard
USW2-xai.grok-4.3-mantle-input-tokens-standard
USW2-xai.grok-4.3-mantle-output-tokens-standard
USW2-xai.grok-4.6-mantle-cache-read-tokens-standard
USW2-xai.grok-4.6-mantle-input-tokens-standard
USW2-xai.grok-4.6-mantle-output-tokens-standard
The USAGE_TYPE for Grok 4.6 is <region prefix>-xai.grok-4.6-mantle-<input|output|cache-read>-tokens-standard. It follows the same naming convention as the mantle-type values for gpt-oss 120B and Gemma 4 31B, and all of them are classified under Amazon Bedrock. Values in a different format that contain neither the provider name nor mantle, such as USE2-gpt-oss-120b-input-tokens in the list, also coexist. For cross-Region inference via the global profile, the USAGE_TYPE suffix becomes global-standard. In the list, APN1-xai.grok-4.6-mantle-input-tokens-global-standard corresponds to this.
The full output of the command above without the grep filter also included USAGE_TYPEs for Qwen, DeepSeek, Mistral, MiniMax, Kimi, Nemotron, GLM, and Nova. USAGE_TYPEs for Claude and OpenAI GPT-5.x did not appear.
Billing Entity
In this aggregation, even for models called via Bedrock, the billing entity was split between AWS and AWS Marketplace.
The Billing Entity for Grok 4.6 Is AWS
For August 2026, I aggregated the 7 USAGE_TYPEs corresponding to Grok 4.6 by BILLING_ENTITY and RECORD_TYPE. As in the previous section, these are the results from the working account with no credits. The billing entity was AWS, and the only row in the retrieved results had a RECORD_TYPE of Usage. Because the billed amount was not yet finalized at the time of retrieval, the values are estimates.
Billing entity for Grok 4.6 (full command and output)
aws ce get-cost-and-usage \
--time-period Start=2026-08-01,End=2026-09-01 \
--granularity MONTHLY --metrics UnblendedCost \
--filter '{"Dimensions":{"Key":"USAGE_TYPE","Values":["APN1-xai.grok-4.6-mantle-input-tokens-global-standard","APN1-xai.grok-4.6-mantle-output-tokens-global-standard","USE1-xai.grok-4.6-mantle-input-tokens-standard","USE1-xai.grok-4.6-mantle-output-tokens-standard","USW2-xai.grok-4.6-mantle-cache-read-tokens-standard","USW2-xai.grok-4.6-mantle-input-tokens-standard","USW2-xai.grok-4.6-mantle-output-tokens-standard"]}}' \
--group-by '[{"Type":"DIMENSION","Key":"BILLING_ENTITY"},{"Type":"DIMENSION","Key":"RECORD_TYPE"}]'
{
"GroupDefinitions": [
{
"Type": "DIMENSION",
"Key": "BILLING_ENTITY"
},
{
"Type": "DIMENSION",
"Key": "RECORD_TYPE"
}
],
"ResultsByTime": [
{
"TimePeriod": {
"Start": "2026-08-01",
"End": "2026-09-01"
},
"Total": {},
"Groups": [
{
"Keys": [
"AWS",
"Usage"
],
"Metrics": {
"UnblendedCost": {
"Amount": "0.0182128794",
"Unit": "USD"
}
}
}
],
"Estimated": true
}
],
"DimensionValueAttributes": []
}
The Billing Entity for Claude Opus 5 and OpenAI GPT-5.6 Is AWS Marketplace
For August 2026 in this account, I narrowed the billing entity to AWS Marketplace and aggregated by service.
aws ce get-cost-and-usage \
--time-period Start=2026-08-01,End=2026-09-01 \
--granularity MONTHLY --metrics UnblendedCost \
--filter '{"Dimensions":{"Key":"BILLING_ENTITY","Values":["AWS Marketplace"]}}' \
--group-by '[{"Type":"DIMENSION","Key":"SERVICE"},{"Type":"DIMENSION","Key":"RECORD_TYPE"}]' \
| jq -r '.ResultsByTime[].Groups[]|[.Keys[0],.Keys[1],.Metrics.UnblendedCost.Amount]|@tsv'
Claude Opus 5 (Amazon Bedrock Edition) Usage 0.0000715
OpenAI GPT-5.6 Luna (Amazon Bedrock Edition) Usage 1.4188744473
OpenAI GPT-5.6 Sol (Amazon Bedrock Edition) Usage 0.002095
OpenAI GPT-5.6 Terra (Amazon Bedrock Edition) Usage 0.08698026
Tax Tax 0
In the AWS Marketplace aggregation, Claude Opus 5 and OpenAI GPT-5.6 (Luna / Sol / Terra), called via Bedrock, were each listed as independent services. Grok 4.6 is not included in this list.
Credit Offsets
Separately from the working account with no credits, I also aggregated August 2026 for an account that holds AWS credits and used Grok 4.6 in us-west-2. The target was SERVICE of Amazon Bedrock and the 2 USAGE_TYPEs corresponding to Grok 4.6 input and output tokens. I aggregated by RECORD_TYPE and USAGE_TYPE. Because the billed amount was not yet finalized at the time of retrieval, the values are estimates.
Credit USW2-xai.grok-4.6-mantle-input-tokens-standard -0.0000000836
Credit USW2-xai.grok-4.6-mantle-output-tokens-standard -0.000002046
Usage USW2-xai.grok-4.6-mantle-input-tokens-standard 0.0000000836
Usage USW2-xai.grok-4.6-mantle-output-tokens-standard 0.000002046
For each of input tokens and output tokens, a Credit row of the same amount as Usage was recorded, and the total came to 0. Aggregating the same data by billing entity also showed Usage and Credit of the same amount under AWS. Credits had been applied to the Grok 4.6 usage charges billed by AWS.
The products eligible for the credits I checked included Amazon Bedrock. You can check which products your own AWS credits apply to in the credit list in the Billing console.
Summary
If Amazon Bedrock is included among the products eligible for your AWS credits, those credits can also be applied to Grok 4.6 usage charges. If you are looking for a high-performance LLM you can use with credits, please consider trying Grok 4.6 as one of your candidates.
