Added GPT-6.1 Sol: Added the GPT-6.1 Sol model card and updated the OpenAI catalog and availability references. GPT-6.1 Sol is available on the Mantle endpoint in US East (N. Virginia) and through US geographic cross-Region inference on bedrock-runtime. Th

OpenAI — GPT-6.1 Sol

Model launch date: September 29, 2026. Follows OpenAI first-party lifecycle terms with at least 6 months of deprecation notice for generally available models. Model lifecycle: Active.

Model Details

• Context window: 1M tokens
• Max output tokens: 131,072 tokens

Endpoints and APIs supported

• Endpoint: bedrock-runtime, bedrock-mantle
• APIs: Messages, Responses, Chat Completions, Converse, Invoke

Capabilities and Features

• Response streaming: Not Supported
• Guardrails: Not Supported
• Server-side system tools: Not Supported
• Intelligent prompt routing: Not Supported
• Count tokens: Not Supported
• Explicit prompt caching: Not Supported

Pricing

• Commercial Regions — short context (272K input tokens or fewer):
• Input: $2.20
• Input — cache write: $2.75
• Input — cache read: $0.11
• Output: $11.00
• Commercial Regions — long context (more than 272K input tokens):
• Input: $4.40
• Input — cache write: $5.50
• Input — cache read: $0.22
• Output: $16.50

Programmatic Access

• Endpoint: bedrock-mantle, bedrock-runtime
• Model ID: openai.gpt-6.1-sol
• In-Region endpoint URL: https://bedrock-mantle.us-east-1.api.aws/openai/v1
• Geo inference ID: Not supported
• Global inference ID: Not supported

Regional Availability

• bedrock-mantle: Available in us-east-1 (N. Virginia, IAD)
• bedrock-runtime: US geographic inference profile

Quotas and Limits

• Output-token burndown rate: 10: each output token consumes 10 tokens of quota

Sample Code

• Step 1 - AWS Account: Sign up for an AWS account
  
  
  

  If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.