GPT-4o mini
Low-cost OpenAI family for high-volume chat, classification, and lightweight tool tasks.
- Input
- $0.15 / 1M tokens
- Output
- $0.60 / 1M tokens
- Cached read
- $0.07 / 1M tokens
- Cached write
- $0.15 / 1M tokens
- Batch discount
- 50%
- Source
- OpenAI API pricing
- Verified
- Apr 1, 2026 (High)
Capabilities
- Modalities
- textimage→text
- Capabilities
- webSearchimageInputbatchSupportpromptCachingfunctionCallingstructuredOutputs
- Strengths
- Lowest-cost OpenAI text family, Good throughput for agent fan-out, Useful multimodal input support
- Tradeoffs
- Less robust reasoning than GPT-5.4, Smaller output budget
Benchmark Coverage
| Benchmark | Version | Score | Date | Source | Notes |
|---|---|---|---|---|---|
| MMLU | 2025-rolling | 82.4 accuracy | Dec 12, 2025 | OpenAI model guide | Use for directional comparison only. |
Release History
| Release | Alias | Lifecycle | Release Date | Deprecation | Shutdown | Summary |
|---|---|---|---|---|---|---|
| GPT-4o mini | gpt-4o-mini | Active | Jul 18, 2024 | — | — | Cost-efficient family released for high-volume production traffic. |
Host Coverage
| Host | Type | Context | Pricing Note | Differences |
|---|---|---|---|---|
| OpenAI API | first-party | 128.0K | Reference pricing and full tool support. | Prompt caching; Batch API |
| Azure OpenAI | cloud | 128.0K | Enterprise hosting with separate regional rollouts. | Azure quota management |
Migration Guidance
Default cost-down migration target for GPT-4o or GPT-5.4 traffic that does not need top-end reasoning.
Replacement models: gpt-5-4
Breaking changes: Reasoning depth and output budget are reduced versus flagship families.
Change Events
| Date | Type | Title | Description | Source |
|---|---|---|---|---|
| Jul 18, 2024 | family_added | Family launched | GPT-4o mini launched as OpenAI's low-cost production family. | OpenAI changelog |
Other models from OpenAI
GPT-4.1, GPT-4.1 mini, GPT-4.1 nano, GPT-4o, GPT-5.4, GPT-5.4 mini, GPT-5.4 nano