Compare
GPT-4o Mini vs GPT-5 Nano
Price, speed, lengths, sizes, inputs and plan for GPT-4o Mini and GPT-5 Nano, side by side, with example outputs from each.
Side by side
| Fact | GPT-4o Mini | GPT-5 Nano |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Makes | Agent & text | Agent & text |
| Best at | Ask and write | Ask and write |
| Price per unit | about $0.158 in / $0.63 out per 1M tokens | about $0.052 in / $0.42 out per 1M tokens |
| Typical run | about $0.000472 (1,000 input + 500 output tokens) | about $0.000263 (1,000 input + 500 output tokens) |
| Takes | Text | Text |
| Success rate Last 30 days | — | — |
| Median time Last 30 days | — | — |
| Plan needed | Free | Free |
A dash means we do not have that figure for the model. Success rate and median time cover the last 30 days and appear once a model has enough runs.
Example outputs
Questions
- Which plan do I need for GPT-4o Mini and GPT-5 Nano?
- GPT-4o Mini: Runs on any account, including the Free plan. GPT-5 Nano: Runs on any account, including the Free plan.
- Who makes GPT-4o Mini and GPT-5 Nano?
- GPT-4o Mini is made by OpenAI and GPT-5 Nano is made by OpenAI.
Keep looking
How these figures are made
- Success rate and time to result
- Last 30 days of customer runs. Success rate = successful runs / (successful runs + runs that failed on our side or the model's side). Runs refused by a safety filter, runs with invalid settings or missing input, runs stopped by the customer and runs without enough credits are not counted as failures. Time to result = from submitting to the finished result, including any queue wait; we show the median. Figures are hidden until a model has 20 runs in the window.
- Prices
- List price of one unit on the model's default route, in credits and US dollars at 10,000 credits = $1. Plans give credits at their own effective rate; failed or refused runs are not charged.
- Share
- Each model’s share of the week’s successful runs of its type, as a band. We publish ranks and bands, never the number of runs.

