GPT-6 Astra
OpenAI · Active · available in 31 of 31 regions
Tool useVisionPrompt cachingStreaming Batch inferenceEmbeddingsFine-tuning
- Context window
- 1.1M
- 1,050,000 tokens
- Max output
- —
- Input / 1M
- $10.00
- us-east-1
- Output / 1M
- $50.00
What GPT-6 Astra is good for
editorialGPT-6 Astra offers a 1M-token context window with tool use and prompt caching, at the premium end of this provider’s range at $10.00 per 1M input tokens. Callable in 31 of 31 regions.
Suits
- Very long inputs. A 1.1M-token window holds an entire codebase or a day of transcripts in one call, so you can skip chunking.
- Repeated prompts. Supports prompt caching, so a re-sent prefix costs about 10× less than fresh input. On agentic loops that resend a long system prompt every step, this moves the bill more than the headline price does.
- Tool use. Can call functions, so it can drive retrieval, look things up, and take actions rather than only answering.
- Images. Accepts image input: screenshots, scanned documents, charts and UI captures.
Think twice if
- High volume. At $10.00 per 1M input tokens it sits at the expensive end of the OpenAI range. Worth it for hard tasks, wasteful for bulk extraction.
- Invocation. Reachable only through a cross-region inference profile — calling the bare model ID returns a validation error. Use an ID such as global.openai.gpt-6-astra.
This section is judgement, not data from AWS. It is composed from the capabilities, context window, price position and region coverage shown elsewhere on this page — so it stays in step with the daily snapshot rather than going stale.
Where teams typically use it
Agentic workflows
Multi-step work where the model calls tools, reads the results and decides what to do next.
- · A support agent that looks up the order, checks the refund policy and drafts the reply before a human approves it.
- · An on-call assistant that reads logs and metrics, forms a hypothesis, and proposes the one command to run.
- · A migration bot that opens a pull request per file and reruns the test suite between each change.
Coding
Writing, reviewing and refactoring code, usually across more than one file.
- · A review pass that flags real defects with a severity and leaves style alone.
- · A framework upgrade applied across a repository, one module at a time, tests green between each.
- · Turning a failing bug report into a reproducing test and then a fix.
RAG and retrieval
Answering from your own documents, with the retrieved passages in the prompt.
- · An internal search over contracts and policies that quotes the clause it answered from.
- · A product assistant grounded in the current documentation rather than the training data.
- · A research summariser that reads twenty retrieved papers and reconciles where they disagree.
Model & inference profile IDs
Base model ID — direct on-demand invoke
Cross-region inference profiles (2)
Regions marked Inference profile only require a profile ID rather than the base model ID — invoking the base ID there returns a validation error. Regional (us., eu.) profiles carry a 10% premium over global.
Pricing by region
USD per 1M tokens| Region | Input | Output | Cache read | Cache write | Batch in | Batch out | Source |
|---|---|---|---|---|---|---|---|
| us-east-1 US East (N. Virginia) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| us-east-2 US East (Ohio) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| us-west-1 US West (N. California) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| us-west-2 US West (Oregon) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| ca-central-1 Canada (Central) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| ca-west-1 Canada West (Calgary) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| mx-central-1 Mexico (Central) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| eu-west-1 EU (Ireland) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| eu-west-2 EU (London) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| eu-west-3 EU (Paris) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| eu-central-1 EU (Frankfurt) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| eu-central-2 Europe (Zurich) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| eu-north-1 EU (Stockholm) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| eu-south-1 EU (Milan) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| eu-south-2 Europe (Spain) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| ap-east-2 Asia Pacific (Taipei) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| ap-northeast-1 Asia Pacific (Tokyo) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| ap-northeast-2 Asia Pacific (Seoul) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| ap-northeast-3 Asia Pacific (Osaka) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| ap-south-1 Asia Pacific (Mumbai) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| ap-south-2 Asia Pacific (Hyderabad) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| ap-southeast-1 Asia Pacific (Singapore) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| ap-southeast-2 Asia Pacific (Sydney) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| ap-southeast-3 Asia Pacific (Jakarta) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| ap-southeast-4 Asia Pacific (Melbourne) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| ap-southeast-5 Asia Pacific (Malaysia) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| ap-southeast-6 Asia Pacific (New Zealand) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| ap-southeast-7 Asia Pacific (Thailand) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| il-central-1 Israel (Tel Aviv) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| af-south-1 Africa (Cape Town) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
| sa-east-1 South America (Sao Paulo) | $10.00 | $50.00 | $1.00 | $12.50 | — | — | curated |
Curated pricing. The AWS Price List API publishes no SKU for this model, so these figures are hand-maintained from AWS's public pricing page and verified on Sep 15, 2026. They are not machine-derived — confirm in the AWS console before committing spend. Global endpoint, requests up to 272K tokens. Beyond that AWS bills 2x input and 1.5x output. The US-geo profile bills 10% more ($11 / $55).
Region availability
Inference profile only us-east-1 Profile only Inference profile only us-east-2 Profile only Inference profile only us-west-1 Profile only Inference profile only us-west-2 Profile only Inference profile only ca-central-1 Profile only Inference profile only ca-west-1 Profile only Inference profile only mx-central-1 Profile only Inference profile only eu-west-1 Profile only Inference profile only eu-west-2 Profile only Inference profile only eu-west-3 Profile only Inference profile only eu-central-1 Profile only Inference profile only eu-central-2 Profile only Inference profile only eu-north-1 Profile only Inference profile only eu-south-1 Profile only Inference profile only eu-south-2 Profile only Inference profile only ap-east-2 Profile only Inference profile only ap-northeast-1 Profile only Inference profile only ap-northeast-2 Profile only Inference profile only ap-northeast-3 Profile only Inference profile only ap-south-1 Profile only Inference profile only ap-south-2 Profile only Inference profile only ap-southeast-1 Profile only Inference profile only ap-southeast-2 Profile only Inference profile only ap-southeast-3 Profile only Inference profile only ap-southeast-4 Profile only Inference profile only ap-southeast-5 Profile only Inference profile only ap-southeast-6 Profile only Inference profile only ap-southeast-7 Profile only Inference profile only il-central-1 Profile only Inference profile only af-south-1 Profile only Inference profile only sa-east-1 Profile only
TPM / RPM are default account quotas from AWS Service Quotas where a model-specific limit is published. They are per-account defaults and adjustable on request.
Where this model actually runs
Under a strict residency constraint, GPT-6 Astra can be served without the request leaving 1 of the 25 jurisdictions with a Bedrock region.
GPT-6 Astra compared
Side-by-side pages against every model people weigh this one against.
GPT-6 Astra vs Claude Fable 5Same input price.GPT-6 Astra vs Claude Fable 5.1Same input price.GPT-6 Astra vs Claude Haiku 4.5Claude Haiku 4.5 costs 10× less per input token than GPT-6 Astra, and GPT-6 Astra holds 1.1M tokens against 200K for Claude Haiku 4.5.GPT-6 Astra vs Claude Opus 4.5Claude Opus 4.5 costs 2.0× less per input token than GPT-6 Astra, and GPT-6 Astra holds 1.1M tokens against 200K for Claude Opus 4.5.GPT-6 Astra vs Claude Opus 4.6Claude Opus 4.6 costs 2.0× less per input token than GPT-6 Astra.GPT-6 Astra vs Claude Opus 4.7Claude Opus 4.7 costs 2.0× less per input token than GPT-6 Astra.GPT-6 Astra vs Claude Opus 4.8Claude Opus 4.8 costs 2.0× less per input token than GPT-6 Astra.GPT-6 Astra vs Claude Opus 5Claude Opus 5 costs 2.0× less per input token than GPT-6 Astra.GPT-6 Astra vs Claude Sonnet 4.5Claude Sonnet 4.5 costs 3.3× less per input token than GPT-6 Astra, and GPT-6 Astra holds 1.1M tokens against 200K for Claude Sonnet 4.5.GPT-6 Astra vs Claude Sonnet 4.6Claude Sonnet 4.6 costs 3.3× less per input token than GPT-6 Astra.GPT-6 Astra vs Claude Sonnet 5Claude Sonnet 5 costs 5.0× less per input token than GPT-6 Astra.GPT-6 Astra vs GPT-5.6 LunaGPT-5.6 Luna costs 50× less per input token than GPT-6 Astra.GPT-6 Astra vs GPT-5.6 SolGPT-5.6 Sol costs 2.5× less per input token than GPT-6 Astra.GPT-6 Astra vs GPT-5.6 TerraGPT-5.6 Terra costs 5.0× less per input token than GPT-6 Astra.GPT-6 Astra vs Grok 4.6Grok 4.6 costs 5.0× less per input token than GPT-6 Astra, and GPT-6 Astra holds 1.1M tokens against 500K for Grok 4.6.
GPT-6 Astra appears in
Common questions
- How much does GPT-6 Astra cost on Amazon Bedrock?
- $10.00 per 1M input tokens and $50.00 per 1M output tokens in us-east-1. Cached input reads at $1.00, roughly a tenth of the input rate, which dominates the bill on agentic workloads that re-send a long prefix.
- Which AWS regions support GPT-6 Astra?
- 31 of 31 regions: us-east-1, us-east-2, us-west-1, us-west-2, ca-central-1, ca-west-1, mx-central-1, eu-west-1, eu-west-2, eu-west-3, eu-central-1, eu-central-2, eu-north-1, eu-south-1, eu-south-2, ap-east-2, ap-northeast-1, ap-northeast-2, ap-northeast-3, ap-south-1, ap-south-2, ap-southeast-1, ap-southeast-2, ap-southeast-3, ap-southeast-4, ap-southeast-5, ap-southeast-6, ap-southeast-7, il-central-1, af-south-1, sa-east-1. Regions marked profile-only need a cross-region inference profile ID such as global.openai.gpt-6-astra rather than the bare model ID.
- What is the context window of GPT-6 Astra?
- 1,050,000 tokens (1.1M).
- What is the model ID for GPT-6 Astra on Bedrock?
- openai.gpt-6-astra. In regions where it is only reachable through a cross-region inference profile, use a prefixed ID instead: global.openai.gpt-6-astra, us.openai.gpt-6-astra.