Historical model (deprecated). The rates below are the last recorded rates, not a recommendation for a new deployment.
OpenAI shut down this API model on 2026-10-23.
o3-mini API Pricing
OpenAI shut down this API model on 2026-10-23. No directly comparable current token quote is available. These rates were last verified on .
Moving off o3-mini?
Same token usage, 3:1 input:output, standard list rates · excludes cache, batch and fast mode. Not a quality or compatibility claim. Full calculator →
OpenAI reasoning pricing history
USD · units shown per rateNewest first. Release dates describe the model, not when today's rates took effect. Observations show when we recorded rates, not launch pricing. Image and text token meters are separate; no fixed image-token savings mix is assumed. How we verify
OpenAI shut down this API model on 2026-10-23.
Published rates and billing units
| Billing dimension | USD list price |
|---|
Verified 2026-11-12 · Official source · Pricing methodology. Taxes, optional services and account-specific discounts are not included.
Cost examples
These examples use published list prices only. They exclude taxes, enterprise discounts, minimum charges, retries, batch discounts, and provider-specific billing rules.
1M input + 1M output
—
A direct per-million comparison against every other text model.
100K input + 25K output
—
A compact chat, summarization, or analysis workload.
10M input + 2M output
—
A monthly production estimate for heavier RAG or agent traffic.
75% cached input + 250K output
Not listed
OpenAI does not publish a cached-input rate for this model in our dataset.
Calculator for o3-mini
Enter your own input, output, and cached-token assumptions. This calculator is preloaded with only o3-mini, so the result stays focused on this model.
OpenAI shut down this API model on 2026-10-23. Token-only calculation unavailable.
Price history
No list-price movement across 86 daily snapshots from 2026-08-18 to 2026-11-11.
When to use o3-mini
Good fit
- code generation, debugging, and agentic development work where output quality affects engineering time
- reasoning-heavy prompts, planning, analysis, and multi-step tool use
- high-volume routing, classification, extraction, summaries, and fallback traffic
Be careful with
- production launches until the provider restores availability