OpenAI o4-mini
A fast, cost-efficient reasoning model on a 200K-token context window. Succeeded by GPT-5 mini.
Source: OpenAI models, OpenAI pricing, Prompt caching (1,024 minimum, 30m TTL)
- Text
- Image
- Text
Pricing
Every billing leg from the live catalog, in USD per 1M tokens.
| Billing leg | Rate | Batch |
|---|---|---|
| Input | $1.1 / M | $0.55 / M |
| Output | $4.4 / M | $2.2 / M |
| Cache read | $0.275 / M | n/a |
Cost calculator
Billing-grade math over the rate card above, including the thinking tokens most estimates miss.
Hidden reasoning tokens bill as output. 1.0x = thinking off. Medium-effort reasoning typically lands near 3x; heavy reasoning runs 6x to 8x. Set it to match your workload.
Compare providers
The same model, priced across every platform that serves it. Lowest combined in/out rate is flagged.
| Platform | Region | Input / M | Output / M | Cache read / M | Batch | Access |
|---|---|---|---|---|---|---|
OpenAILowest | - | $1.1 | $4.4 | $0.275 | ✓ | First-party API |
Azure OpenAI | - | $1.1 | $4.4 | $0.275 | ✓ | Direct |
Azure OpenAI · Data zone | - | $1.21 | $4.84 | $0.303 | ✓ | Direct |
Azure OpenAI · Regional | $1.21 | $4.84 | $0.303 | - | Direct |
Some hosts price by region. Shown rates match the selected region.
Price history
Has this model gotten cheaper or more expensive?
| Effective | Input / Output | Status |
|---|---|---|
| April 20, 2026 – July 10, 2026 | $1.1 / $4.4 | past |
| July 10, 2026 – August 3, 2026 | $1.1 / $4.4 | past |
| August 3, 2026 | $1.1 / $4.4 | current |
More from OpenAI
Other models from the same provider.
Stop estimating. Track it.
SuperPenguin meters every OpenAI o4-mini call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.
Rates are generated from SuperPenguin's live pricing catalog.