Most demanding reasoning and coding workloads, frontier agentic systems
Stored values, not live provider measurements.
| Provider | OpenAI |
| Category | Reasoning |
| Input cost / 1M tokens | $10.00 |
| Output cost / 1M tokens | $50.00 |
| Cache read / 1M tokens | $1.00 |
| Context window | 1.1M tokens |
| Max output | 128k tokens |
| Batch API | Supported |
| Vision | Supported |
| Vision price / 1k images | Billed as tokens |
| Speed rating | Deliberate |
| Intelligence score | 57/100 |
| Throughput | 47 tokens/sec |
| Time to first token | 192.00s |
| Hardware | Not disclosed by provider |
Enter your own input, output, caching, and batch assumptions in the calculator.
Open calculatorPricing review: 11/4/2026
Performance review: 11/4/2026
GPT-6 Astra costs $10.000 per 1M input tokens and $50.000 per 1M output tokens in the stored catalog. Blended cost depends on your input/output mix.
GPT-6 Astra has a context window of 1.1M tokens (1,050,000 tokens). This is the maximum combined input and output for a single request.
GPT-6 Astra is currently offered by OpenAI. Pricing is a stored catalog value — confirm current rates with the provider.