GPT-6 Astra: API Pricing, Context Window and Specs
GPT-6 Astra is OpenAI’s most capable model for complex reasoning, coding, computer use, research and document creation. It is available through the OpenAI API.
Standard API pricing is $10 per million input tokens and $50 per million output tokens. Cached input costs $1 per million tokens. These are token prices; the cost of a CAD task depends on the tokens and tools it uses.
- Input
- $10
- Output
- $50
- Cached input
- $1
- Cache write
- $12.50
- Batch
- 50% off
- Over 272K input
- $20 / $75
USD per 1M tokens, standard tier. Source: OpenAI pricing, checked Oct 21, 2026.
For engineering task costs, see the SKY-001 vs GPT-6 Astra comparison and its self-reported benchmark caveats.
Quick estimate
GPT-6 Astra pricing details
- Official prices checked October 21, 2026. All rates are in USD per 1M tokens.
- Cache writes cost $12.50 per 1M tokens at the standard short-context rate. Cached reads cost $1 per 1M tokens.
- Above 272K input tokens, the full request uses long-context rates: $20 input, $2 cached input and $75 output per 1M tokens. Cache rates also double.
- Batch and Flex processing cost 50% of standard rates. Fast mode costs twice the applicable rates.
- The estimate covers token charges. Tool calls, retries and reasoning output tokens can increase the final bill.
What GPT-6 Astra costs in practice
Standard-tier cost with no caching, for a few common request shapes.
| Workload | Tokens in / out | Per request | Per 10,000 requests |
|---|---|---|---|
| Chatbot | 500 / 300 | $0.02 | $200 |
| RAG Q&A | 4,000 / 500 | $0.065 | $650 |
| Coding agent | 30,000 / 2,000 | $0.40 | $4,000 |
| Summarization | 8,000 / 600 | $0.11 | $1,100 |
GPT-6 Astra specs
- Context window
- 1.05M
- Max output tokens
- 128K
- Released
- Sep 3, 2026
- API model ID
- gpt-6-astra
- Knowledge cutoff
- Apr 30, 2026
- Input / output
- Text and image in, text out
- Reasoning effort
- low, medium, high, xhigh, max
From the official model page.
GPT-6 Astra vs similar models
| Model | Provider | Input $/1M | Output $/1M | Cached $/1M | Context |
|---|---|---|---|---|---|
| GPT-6 Astra OpenAI | OpenAI | $10 | $50 | $1 | 1.05M |
| GPT-6.1 Sol OpenAI | OpenAI | $2 | $10 | $0.10 | 1.05M |
| GPT-6 Sol OpenAI | OpenAI | $2 | $10 | $0.20 | 1.05M |
| Claude Opus 5.5 | Anthropic | $4 | $20 | $0.20 | 1M |
GPT-6 Astra FAQ
Standard pricing is $10 per 1M input tokens, $50 per 1M output tokens and $1 per 1M cached input tokens. Above 272K input tokens, the full request costs $20 input, $75 output and $2 cached input per 1M tokens.
Yes. GPT-6 Astra is available through the OpenAI API under the model ID gpt-6-astra.
Yes. Batch and Flex processing cost 50% of standard rates: $5 input and $25 output per 1M tokens for short-context requests.
Skyfall reports similar CAD shape match with lower time and cost for SKY-001 in its own benchmark. These results are self-reported and have not been independently verified. SKY-001 is waitlist-only and has no public API price. Read the SKY-001 vs GPT-6 Astra comparison.
Related tools
- LLM API pricing tableEvery model's input, output and cached rates in one sortable table.
- LLM Price ComparisonPut two to four models side by side: per-token rates, context window, discounts and what the same job costs on each.
- Cheapest LLM APIsRanked lists of the lowest-priced models overall, among flagships, with 1M-token context, with image input and with open weights.
- Token Cost CalculatorEnter a token count and see what that many input and output tokens cost on every model.
- LLM Cost CalculatorPick a workload and request volume, and compare the bill across models with caching and batch discounts.