o3 Mini High API Pricing
OpenAI · Mid-tier · Proprietary · released 2025-02. Prices in USD per 1 million tokens. Data snapshot: 2026-08-14.
- Input: $1.10 per 1M tokens
- Output: $4.40 per 1M tokens
- Batch API (input/output): $0.55 / $2.20
- Prompt-cache read: $0.55
- Context window: 200K
- Arena ELO: 1337 (as of 2026-08-13)
Cost per request by business use case
List price vs optimized (prompt caching on the cached input share, batch API for async workloads — only where the provider publishes those rates).
| Use case | Tokens (in/out) | Cost/req (list) | Cost/req (optimized) | Monthly @100K req |
|---|---|---|---|---|
| Support Ticket | 1,500 / 500 | $0.0039 | $0.0034 | $336 |
| Knowledge Q&A | 2,000 / 800 | $0.0057 | $0.0050 | $495 |
| Meeting Summary | 10,000 / 1,200 | $0.016 | $0.0081 | $814 |
| Marketing Content | 2,500 / 1,800 | $0.011 | $0.010 | $1.0K |
| Coding Task | 3,000 / 2,000 | $0.012 | $0.011 | $1.1K |
| Invoice Processing | 1,500 / 600 | $0.0043 | $0.0021 | $215 |
| Call Summary | 2,000 / 700 | $0.0053 | $0.0026 | $264 |
| Agent Workflow | 6,000 / 3,000 | $0.020 | $0.017 | $1.7K |
These are list prices — real cost also depends on caching, batching, negotiated discounts, marketplace agreements, and existing contracts. Get a FinOps review from OptimNow or compare all models.