Calculate the cost of using us.openai.gpt-6-astra from AWS Bedrock for your AI applications
Pricing data last updated:
Mode: Responses
Max: 1,050,000 tokens
Max: 128,000 tokens
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
us.openai.gpt-6-astra is a responses model from AWS Bedrock, one of 2 responses models they offer. It is priced at $11.00 per 1M input tokens and $55.00 per 1M output tokens, ranking 92 out of 115 responses models by cost and cheaper than 20% of models in this category. us.openai.gpt-6-astra supports vision, function calling, reasoning, prompt caching — one of only 3 responses models with this combination. Its 1,050K-token context window is in the top 26% among responses models.
Note: Use the interactive calculator above to estimate costs for your specific usage patterns.
Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 1,050,000 input tokens. The maximum output length is 128,000 tokens.
At $11.00 per 1M input tokens and $55.00 per 1M output tokens, us.openai.gpt-6-astra ranks 92 out of 115 responses models by input cost. It is more expensive compared to the median of $2.00 for responses models, and is cheaper than 20% of models in this category.
us.openai.gpt-6-astra is one of 2 AWS Bedrock responses models, one of only 3 responses models combining function calling, prompt caching, reasoning, vision. its 1,050K-token context window places it in the top 26% of responses models.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs us.openai.gpt-6-astra |
|---|---|---|---|---|
| o3-deep-research | Azure | $10.00 | $40.00 | -9% |
| gpt-daybreak-red-latest | OpenAI | $12.50 | $75.00 | +14% |
| o3-deep-research | OpenAI | $10.00 | $40.00 | -9% |
Similar responses models from other providers
No. us.openai.gpt-6-astra costs $11.00 per 1M input tokens while o3-deep-research costs $10.00 per 1M input tokens, making o3-deep-research 9% more affordable for input. However, us.openai.gpt-6-astra may offer different capabilities or performance characteristics that justify the price difference.
us.openai.gpt-6-astra input pricing is $11.00 per 1M tokens, which is 450% above the median of $2.00 for responses models. It ranks 92 out of 115 responses models by input cost, making it cheaper than 20% of models in this category. For output, it costs $55.00 per 1M tokens compared to the median of $13.20.
Among AWS Bedrock's 2 responses models, us.openai.gpt-6-astra ranks 2 by input cost. Its combination of function calling, prompt caching, reasoning, vision is shared by only 2 other responses models.
The most comparable responses models to us.openai.gpt-6-astra are: o3-deep-research from Azure ($10.00/1M input tokens); gpt-daybreak-red-latest from OpenAI ($12.50/1M input tokens); o3-deep-research from OpenAI ($10.00/1M input tokens); o3-deep-research-2025-06-26 from OpenAI ($10.00/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.
us.openai.gpt-6-astra supports up to 1,050,000 input tokens, placing it in the top 26% of responses models by context window size (rank 14 of 73). This makes it suitable for processing long documents, extensive code repositories, or maintaining detailed conversation histories.
us.openai.gpt-6-astra is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $11.00 and generating 1M output tokens costs $55.00.