GPT-6.2 Astra
OpenAI — GPT-6.2 Astra
Model Details
GPT-6.2 Astra is the next generation of GPT-6 Astra. It is OpenAI's frontier model for complex, multistep projects such as implementing and testing changes in existing codebases and producing professional deliverables (slides, spreadsheets, documents). It launches with an Ultrafast speed tier for latency-sensitive applications.
Model launch date: November 17, 2026
EOL no sooner than: November 17, 2027
Legacy period: at least 6 months
Model lifecycle policy: Model lifecycle
Model EOL date: N/A
End User License Agreements and Terms of Use: View
Model lifecycle: Active
Context window: 1,050,000 tokens
Max output tokens: 128,000
| Input Modalities | Output Modalities |
|---|---|
Endpoints and APIs supported
The following tables show which endpoints and APIs GPT-6.2 Astra supports. For more information, see APIs supported by Amazon Bedrock and Inference endpoints supported by Amazon Bedrock.
Endpoint support
| Endpoint | Supported |
|---|---|
bedrock-runtime | |
bedrock-mantle |
APIs supported on bedrock-runtime
| Messages | Responses | Chat Completions | Converse | Invoke |
|---|---|---|---|---|
APIs supported on bedrock-mantle
| Messages | Responses | Chat Completions | Converse | Invoke |
|---|---|---|---|---|
On bedrock-mantle, both APIs use the /openai/v1 base path, not /v1. Use either API with this model:
For Responses, use
/openai/v1/responses.For Chat Completions, use
/openai/v1/chat/completions.
Capabilities and Features
Bedrock Features
Features supported using bedrock-runtime
| Supported | Not Supported |
|---|---|
|
Features supported using bedrock-mantle
| Supported | Not Supported |
|---|---|
|
JSON Schema output on bedrock-runtime
Use JSON Schema to set the format of the model response. These settings apply to non-streaming calls on the bedrock-runtime endpoint. Choose a profile ID from Programmatic access.
For Chat Completions, set
response_format.typetojson_schema. Putname,schema, andstrict: trueinresponse_format.json_schema.For Responses, set
text.format.typetojson_schema. Putname,schema, andstrict: trueintext.format.For Converse, set
outputConfig.textFormat.typetojson_schema. InoutputConfig.textFormat.structure.jsonSchema, setnameandschema. Encode the schema as a JSON string. Then setadditionalModelRequestFields.text.format.stricttotrue.
Use an object schema. Put all fields in required. Set additionalProperties to false. Validate your schema before you send it. Check for refusals or incomplete responses before you parse the output.
For JSON Schema output with the Converse API, you must set additionalModelRequestFields.text.format.strict to true, in addition to specifying the schema in outputConfig. Include the following field in your request.
{ "additionalModelRequestFields": { "text": { "format": { "strict": true } } } }
Converse content blocks
On the bedrock-runtime endpoint, Converse accepts text and
image content blocks in user messages. This model doesn't accept
document content blocks, and it doesn't accept an image content block
inside a toolResult. A request that includes either is rejected with a
ValidationException. To send a document to this model, use the Responses API with
an input_file content part instead.
Pricing
All prices are in USD per 1 million tokens.
The Input — 30-minute cache write column is the price per 1 million tokens written to the prompt cache. The 30-minute figure is how long a cached prompt prefix is retained, not a quantity of tokens. For more information, see prompt caching.
Commercial In-Region prices include a 10% fee over OpenAI rates. You do not need to add this fee.
Priority and Flex tiers are not supported for this model.
Standard — Commercial Regions, short context (272K input tokens or fewer)
| Inference option | Input | Input — 30-minute cache write | Input — cache read | Output |
|---|---|---|---|---|
| In-Region | $8.80 | $11.00 | $0.44 | $44.00 |
| Geo CRIS | $8.80 | $11.00 | $0.44 | $44.00 |
| Global CRIS | $8.00 | $10.00 | $0.40 | $40.00 |
Standard — Commercial Regions, long context (more than 272K input tokens)
| Inference option | Input | Input — 30-minute cache write | Input — cache read | Output |
|---|---|---|---|---|
| In-Region | $17.60 | $22.00 | $0.88 | $66.00 |
| Geo CRIS | $17.60 | $22.00 | $0.88 | $66.00 |
| Global CRIS | $16.00 | $20.00 | $0.80 | $60.00 |
Note: GPT-6.2 Astra in Ultrafast mode is available at promotional pricing of 3x the Standard rate through February 28, 2027. Starting March 1, 2027, Ultrafast pricing moves to 6x the Standard rate.
Ultrafast — Commercial Regions, short context (272K input tokens or fewer)
| Inference option | Input | Input — 30-minute cache write | Input — cache read | Output |
|---|---|---|---|---|
| In-Region | $26.40 | $33.00 | $1.32 | $132.00 |
| Geo CRIS | $26.40 | $33.00 | $1.32 | $132.00 |
| Global CRIS | $24.00 | $30.00 | $1.20 | $120.00 |
Ultrafast — Commercial Regions, long context (more than 272K input tokens)
| Inference option | Input | Input — 30-minute cache write | Input — cache read | Output |
|---|---|---|---|---|
| In-Region | $52.80 | $66.00 | $2.64 | $198.00 |
| Geo CRIS | $52.80 | $66.00 | $2.64 | $198.00 |
| Global CRIS | $48.00 | $60.00 | $2.40 | $180.00 |
Programmatic Access
To call this model from code, use the following model IDs and endpoint URLs. For more information, see APIs supported by Amazon Bedrock and Inference endpoints supported by Amazon Bedrock.
| Endpoint | Model ID | In-Region endpoint URL | Geo inference ID | Global inference ID |
|---|---|---|---|---|
bedrock-mantle |
openai.gpt-6.2-astra |
https://bedrock-mantle.{region}.api.aws/openai/v1 |
Not supported | Not supported |
bedrock-runtime |
openai.gpt-6.2-astra |
Not supported | us.openai.gpt-6.2-astra |
global.openai.gpt-6.2-astra |
The bedrock-mantle endpoint is available in us-east-1 (N. Virginia). Ultrafast is available only in us-east-1 on this endpoint. On bedrock-runtime, the base URL is https://bedrock-runtime.{region}.amazonaws.com/openai/v1. Name us.openai.gpt-6.2-astra for US geographic cross-Region inference or global.openai.gpt-6.2-astra for global cross-Region inference.
Service Tiers
Amazon Bedrock offers several service tiers for different workloads. Standard gives you pay-per-token access with no commitment. To use it, set "service_tier": "default" or omit the field. For more information, see service tiers.
Ultrafast is a speed tier for GPT-6.2 Astra. OpenAI reports API speeds up to six times faster than Standard. To request it with the Responses API, set "service_tier": "ultrafast".
| Standard | Ultrafast | Priority | Flex | Reserved |
|---|---|---|---|---|
Use one of these routes for Ultrafast:
bedrock-mantleinus-east-1, with model IDopenai.gpt-6.2-astra.bedrock-runtime, withus.openai.gpt-6.2-astrafor US geographic CRIS orglobal.openai.gpt-6.2-astrafor Global CRIS.
Regional Availability
Regional availability at a glance
Amazon 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 (such as US, EU, and APAC) while respecting data residency, and Global Cross-Region routes anywhere worldwide when there are no residency constraints. Refer to the Regional availability by models page for more details.
Availability differs by endpoint.
Availability using the bedrock-mantle endpoint
| Region | In-Region | Geo | Global |
|---|---|---|---|
us-east-1 (N. Virginia) | |||
us-east-2 (Ohio) | |||
us-west-2 (Oregon) | |||
us-gov-west-1 (GovCloud West) | |||
us-gov-east-1 (GovCloud East) |
Availability using the bedrock-runtime endpoint
| Region | In-Region | Geo | Global |
|---|---|---|---|
us-east-1 (N. Virginia) | |||
us-east-2 (Ohio) | |||
us-west-1 (N. California) | |||
us-west-2 (Oregon) | |||
ca-central-1 (Canada) | |||
ca-west-1 (Calgary) | |||
eu-central-1 (Frankfurt) | |||
eu-central-2 (Zurich) | |||
eu-north-1 (Stockholm) | |||
eu-south-1 (Milan) | |||
eu-south-2 (Spain) | |||
eu-west-1 (Ireland) | |||
eu-west-2 (London) | |||
eu-west-3 (Paris) | |||
ap-east-2 (Taipei) | |||
ap-northeast-1 (Tokyo) | |||
ap-northeast-2 (Seoul) | |||
ap-northeast-3 (Osaka) | |||
ap-south-1 (Mumbai) | |||
ap-south-2 (Hyderabad) | |||
ap-southeast-1 (Singapore) | |||
ap-southeast-2 (Sydney) | |||
ap-southeast-3 (Jakarta) | |||
ap-southeast-4 (Melbourne) | |||
ap-southeast-5 (Malaysia) | |||
ap-southeast-6 (New Zealand) | |||
ap-southeast-7 (Thailand) | |||
il-central-1 (Tel Aviv) | |||
mx-central-1 | |||
me-south-1 (Bahrain) | |||
af-south-1 (Cape Town) | |||
sa-east-1 (São Paulo) |
Geo inference details
The destination Regions available to a geographic inference profile depend on the source Region. To retrieve the current routing configuration, call GetInferenceProfile from the source Region.
Geo: US
Geo inference ID: us.openai.gpt-6.2-astra
| Source Region | Destination Regions |
|---|---|
| us-east-1 (N. Virginia) | us-east-1 (N. Virginia), us-east-2 (Ohio), us-west-2 (Oregon) |
| us-east-2 (Ohio) | us-east-1 (N. Virginia), us-east-2 (Ohio), us-west-2 (Oregon) |
| us-west-1 (N. California) | us-east-1 (N. Virginia), us-east-2 (Ohio), us-west-1 (N. California), us-west-2 (Oregon) |
| us-west-2 (Oregon) | us-east-1 (N. Virginia), us-east-2 (Ohio), us-west-2 (Oregon) |
| ca-central-1 (Canada) | ca-central-1 (Canada), us-east-1 (N. Virginia), us-east-2 (Ohio), us-west-2 (Oregon) |
| ca-west-1 (Calgary) | ca-west-1 (Calgary), us-east-1 (N. Virginia), us-east-2 (Ohio), us-west-2 (Oregon) |
Quotas and Limits
Your AWS account has default quotas. These quotas help keep Amazon Bedrock running well. A few things can change your quotas. These include Region, payment history, fraudulent use, or an approved quota increase request. For more information, see the Quotas for Amazon Bedrock documentation and the limits for the model.
On the bedrock-runtime endpoint, limits are managed as tokens per minute (TPM) with a 10x burndown rate, where 1 output token consumes 10 tokens.
Sample Code
Step 1 - AWS Account: If you already have an AWS account, 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
Step 3 - Get the SDK: You must have Python installed to use this guide. Then install the OpenAI SDK.
pip install openai
Step 4 - Set environment variables
Set up your environment to use the API key for authentication.
On bedrock-runtime, name a cross-Region inference profile as the model: us.openai.gpt-6.2-astra or global.openai.gpt-6.2-astra. This model is not available for in-Region inference on that endpoint.
Step 5 - Run your first inference request
Save the file as bedrock-first-request.py.
bedrock-mantle
Use the settings from Step 4 - Set environment variables. Choose the bedrock-mantle tab. The Chat tab uses the Chat Completions API.
bedrock-runtime: OpenAI SDK
Use the settings from Step 4 - Set environment variables. Choose the bedrock-runtime tab. Send your request with the Responses API.
Ultrafast example
Set OPENAI_API_KEY to your Amazon Bedrock API key. This example uses the bedrock-mantle endpoint in us-east-1.
export OPENAI_API_KEY="<your Amazon Bedrock API key>"
from openai import OpenAI client = OpenAI( base_url="https://bedrock-mantle.us-east-1.api.aws/openai/v1", ) response = client.responses.create( model="openai.gpt-6.2-astra", service_tier="ultrafast", input="Explain how Amazon Bedrock cross-Region inference works.", ) print(response.output_text)
For bedrock-runtime, use the OpenAI-compatible base URL from Programmatic Access. Set the model to us.openai.gpt-6.2-astra for US geographic CRIS or global.openai.gpt-6.2-astra for Global CRIS, and keep service_tier="ultrafast".