Historical model (deprecated). The rates below are the last recorded rates, not a recommendation for a new deployment.
GPT-4o mini API Pricing
GPT-4o mini costs $0.15 per 1M input tokens and $0.60 per 1M output tokens. These rates were last verified on .
Replace an old model
3:1 input:output · standard recorded rates, including historical rates · excludes cache, batch and tier surcharges. Full calculator →
OpenAI small general text pricing history
USD / 1M input · output tokens- $0.10 / $0.50CurrentPrice evidence: 2026-11-08
◌ 0 recorded price changes
- ◌ First observed 2026-09-23 $0.10 / $0.50
- $0.20 / $1.20CurrentPrice evidence: 2026-11-08◌ from 2026-07-31 $0.20 / $1.20
◌ 1 recorded price changes
- ◌ from 2026-07-31 $0.20 / $1.20
- ◌ First observed 2026-06-28 $1.00 / $6.00
- $0.75 / $4.50CurrentPrice evidence: 2026-11-08
◌ 0 recorded price changes
- ◌ First observed 2026-04-16 $0.75 / $4.50
- $0.20 / $1.25Deprecated · 2027-04-01Price evidence: 2026-11-08
◌ 0 recorded price changes
- ◌ First observed 2026-04-16 $0.20 / $1.25
- $0.25 / $2.00Deprecated · 2026-12-11Price evidence: 2026-11-08
◌ 0 recorded price changes
- ◌ First observed 2026-05-16 $0.25 / $2.00
- $0.15 / $0.60Deprecated · 2027-01-14Price evidence: 2026-11-08
◌ 0 recorded price changes
- ◌ First observed 2026-04-16 $0.15 / $0.60
Newest first by official release date, or first recorded observation when release is unknown. Observations are not release dates. Connectors show official replacements only. How we verify
Published rates and billing units
| Billing dimension | USD list price |
|---|---|
| Input / 1M tokens | $0.15 |
| Cached input / 1M tokens | $0.075 |
| Output / 1M tokens | $0.60 |
| Batch: Input / 1M tokens | $0.075 |
| Batch: Output / 1M tokens | $0.30 |
Verified 2026-11-08 · 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
$0.75
A direct per-million comparison against every other text model.
100K input + 25K output
$0.03
A compact chat, summarization, or analysis workload.
10M input + 2M output
$2.70
A monthly production estimate for heavier RAG or agent traffic.
75% cached input + 250K output
$0.2438
Cached input is about 50% cheaper than standard input at list price.
Calculator for GPT-4o mini
Enter your own input, output, and cached-token assumptions. This calculator is preloaded with only GPT-4o mini, so the result stays focused on this model.
Input cost
$0.15
Output cost
$0.60
Total
$0.75
Price history
No list-price movement across 205 daily snapshots from 2026-04-16 to 2026-11-07.
When to use GPT-4o mini
Good fit
- high-volume routing, classification, extraction, summaries, and fallback traffic
Be careful with
- blind migration without testing your own prompts, latency, and failure modes