Standard & Paid Price
The locked value is the exact Paid Price after your first top-up; the discount is derived from the two absolute prices
Unlock with a top-up
| Meter | Standard Price | Paid Price | Save |
|---|---|---|---|
| Input price | $1.0000 / 1M tokens | $0.5500 / 1M tokens | -45% |
| Completion price | $5.0000 / 1M tokens | $2.7500 / 1M tokens | -45% |
| Cache read price | $0.0500 / 1M tokens | $0.0275 / 1M tokens | -45% |
| Cache creation price | $1.2500 / 1M tokens | $1.2500 / 1M tokens | — |
Dynamic pricing · 2 tiers
Billing details
Description
GPT-6.1 Terra via streamed native Responses. Text and function tools; send complete client history. Input above 272000 tokens uses the whole-request long-context tier. Supplier output caps may be exceeded; max_output_tokens is not a reliable spend limit. Cache discounts apply only to reported cache hits.
Capabilities
- Tasks
- chat, reasoning
API endpoints
POST /v1/responses(openai-response)