GPT-6 Astra API pricing
As of October 16, 2026, GPT-6 Astra costs $10.00 per million input tokens and $50.00 per million output tokens on the OpenAI API. Cached input is $1.00 per million.
It is the 32nd cheapest of 36 OpenAI models tracked here, by blended price. The closest Premium-tier model from another provider is Claude Fable 5 (Anthropic) at $10.00 / $50.00, the same blended price. Same list price as Claude Fable 5, Claude Fable 5.1, Claude Mythos 5, Claude Mythos 5.1. First listed in the LiteLLM price data on September 3, 2026. Prompts longer than 272K tokens are billed at $20.00 input / $75.00 output.
Input / 1M tokens$10.00
Output / 1M tokens$50.00
Context window922K
Max output128K
Every published rate
| Rate | Per 1M tokens |
|---|
| Input (standard) | $10.00 |
| Output (standard) | $50.00 |
| Cached input (read) | $1.00 |
| Cache write | $12.50 |
| Batch input | $5.00 |
| Batch output | $25.00 |
| Input, prompts over 272K tokens | $20.00 |
| Output, prompts over 272K tokens | $75.00 |
What it costs in practice
| Task | Tokens | Per request | Per 1,000 requests |
|---|
| Chatbot reply | 1,000 in / 500 out | $0.04 | $35.00 |
| Summarize a long document | 20,000 in / 1,000 out | $0.25 | $250 |
| Coding agent step | 50,000 in / 2,000 out | $0.60 | $600 |
Standard rates, no caching or batch discount; prompts over 272K tokens are billed at the higher long-prompt rate. Compare your own numbers across all models →
Price history
Dates are when each change first appeared in the LiteLLM price data, usually within days of the provider's announcement.
Details
| Provider | OpenAI |
| Price tier | Premium |
| Features | Vision, Reasoning, Prompt caching, Tool use, PDF input, Web search |
| API model names | gpt-6-astra |
| Official pricing | developers.openai.com |
Models at a similar price
Other OpenAI models