GPT-4o Mini.
Cheap multimodal default — replaced GPT-3.5 Turbo for low-cost workloads.
No self-host path — closed weights.
GPT-4o Mini's weights aren't published. Use it via the access providers below.
Cheapest hosted endpoints.
Speed across providers.
Tokens/sec and time-to-first-token measured against the same prompt template on each provider's API.
| Provider | Tokens/sec | TTFT | Total |
|---|---|---|---|
| OpenRouter | 34.8 | 1446 ms | 3588 ms |
Variants in the GPT family.
Frequently asked.
How do I run GPT-4o Mini?
Where can I access GPT-4o Mini?
How much does it cost to run GPT-4o Mini?
Is GPT-4o Mini open-source or proprietary?
What it costs per month across providers.
Estimate your monthly bill for GPT-4o Mini across every host that publishes per-token pricing. Slide your token volumes; the chart + table re-rank cheapest-first.
Cheapest provider on the left.
Total monthly cost — input + output tokens combined.
Bill breakdown.
What it's best at.
Scores normalised against benchmark ceilings (100 = perfect). Coloured by tier — coral 80+ frontier, lavender 65+ strong, sage 50+ solid, slate below.
About GPT-4o Mini.
GPT-4o Mini is OpenAI's cost-sensitive multimodal model — drop-in replacement for GPT-3.5 Turbo at half the price. Supports vision, JSON mode, function calling. 128K context. Most teams use it for high-volume classification, routing, autocomplete, and other cost-dominated workloads where Sonnet/Opus/GPT-5 would be overkill.