Grok 4.3

xAI — Grok 4.3

Model Details

Grok 4.3 is xAI's reasoning-first model with always-on and configurable reasoning effort (low, medium, high). It offers strong tool use and instruction-following capabilities for building multi-step agents, and token efficiency for high-volume inference. Grok 4.3 is especially well suited to enterprise workloads such as contract review, case law research, credit agreement analysis, and financial document Q&A, while delivering consistent quality across conversational AI and multi-turn workflows. Grok 4.3 runs on Mantle, a new inference engine in Amazon Bedrock designed for price performance, with support for tool calling, structured output, and response streaming.

• Model launch date: June 15, 2026

• Model EOL date: N/A

• End User License Agreements and Terms of Use: View

• Model lifecycle: Active

• Context window: 1M tokens

• Reasoning: Supported (configurable: low, medium, high)

Input Modalities	Output Modalities	APIs supported	Endpoints supported
Audio	Embedding	Chat Completions	bedrock-runtime
Image	Image	Responses	bedrock-mantle
Speech	Speech	Invoke
Text	Text	Converse
Video	Video

Note

This model is available on the openai/v1/responses path on the bedrock-mantle endpoint. This is different from the v1/responses path used by other models on the responses endpoint.

Capabilities and Features

Bedrock Features

Features supported using bedrock-mantle endpoint

Supported	Not Supported
Client-side tool calling Reasoning Projects Abuse detection Response streaming Structured outputs	—

Pricing

For pricing, please refer to the Amazon Bedrock Pricing page.

Programmatic Access

Use the following model IDs and endpoint URLs to access this model programmatically. For more information about the available APIs and endpoints, see APIs supported and Endpoints supported.

Endpoint	Model ID	In-Region endpoint URL	Geo inference ID	Global inference ID
bedrock-mantle	xai.grok-4.3	https://bedrock-mantle.{region}.api.aws/openai/v1	Not supported	Not supported

For example, if region is us-west-2 (Oregon), then the bedrock-mantle endpoint URL will be "https://bedrock-mantle.us-west-2.api.aws/openai/v1".

Service Tiers

Amazon Bedrock offers multiple service tiers to match your workload requirements. Standard provides pay-per-token access with no commitment. Priority offers higher throughput with a time-based commitment. Flex provides lower-cost access for flexible, non-time-sensitive workloads. Reserved provides dedicated throughput with a term commitment for predictable workloads. For more information, see service tiers.

Standard	Priority	Flex	Reserved

Regional Availability

Regional availability at a glance

Bedrock offers three inference options: In-Region keeps requests within a single Region for strict compliance, Geo Cross-Region routes across Regions within a geography (US, EU, etc.) for higher throughput while respecting data residency, and Global Cross-Region routes anywhere worldwide for maximum throughput when there are no residency constraints. Refer to the Regional availability page for more details.

Region	In-Region	Geo	Global
us-west-2 (Oregon)

Quotas and Limits

Your AWS account has default quotas to maintain the performance of the service and to ensure appropriate usage of Amazon Bedrock. The default quotas assigned to an account might be updated depending on regional factors, payment history, fraudulent usage, and/or approval of a quota increase request. For more details, please refer to Quotas for Amazon Bedrock documentation and see the limits for the model.

Sample Code

Step 1 - AWS Account: If you have an AWS account already, skip this step. If you are new to AWS, sign up for an AWS account.

Step 2 - API key: Go to the Amazon Bedrock console and generate a long-term API key.

Step 3 - Get the SDK: To use this getting started guide, you must have Python already installed. Then install the relevant software depending on the APIs you are using.

Chat Completions API

pip install openai

Responses API

pip install openai

Step 4 - Set environment variables: Configure your environment to use the API key for authentication.

Chat Completions API

OPENAI_API_KEY="<provide your Bedrock API key>"
OPENAI_BASE_URL="https://bedrock-mantle.us-west-2.api.aws/openai/v1"

Responses API

OPENAI_API_KEY="<provide your Bedrock API key>"
OPENAI_BASE_URL="https://bedrock-mantle.us-west-2.api.aws/openai/v1"

Step 5 - Run your first inference request: Save the file as bedrock-first-request.py

Chat Completions API

from openai import OpenAI

client = OpenAI()

response = client.chat.completions.create(
    model="xai.grok-4.3",
    messages=[
        {"role": "user", "content": "Can you explain the features of Amazon Bedrock?"}
    ]
)
print(response)

Responses API

from openai import OpenAI

client = OpenAI()

response = client.responses.create(
    model="xai.grok-4.3",
    input="Can you explain the features of Amazon Bedrock?"
)
print(response)

Usage Considerations and Limitations

• Reasoning effort — Reasoning is always active by default. You can configure effort via the reasoning parameter: {"effort": "none"} (disables reasoning), "low" (default), "medium", or "high". Reasoning content is encrypted and can be returned by passing include: ["reasoning.encrypted_content"] in the Responses API request. You can send the encrypted content back in subsequent turns to provide reasoning context for multi-turn conversations. The Chat Completions API does not return reasoning tokens.

  response = client.responses.create(
      model="xai.grok-4.3",
      reasoning={"effort": "high"},
      include=["reasoning.encrypted_content"],
      input="Explain quantum entanglement simply."
  )
  print(response.output_text)

• Default parameters — Grok 4.3 uses defaults that differ from the standard OpenAI API specification: temperature defaults to 0.7 (not 1), top_p defaults to 0.95 (not 1), and max_completion_tokens defaults to 131072. Adjust these values explicitly if your application requires different behavior.