GPT-4o
Previous-generation OpenAI multimodal family that remains widely deployed but now sits behind GPT-5.4 for flagship use cases.
- Input
- $2.50 / 1M tokens
- Output
- $10.00 / 1M tokens
- Cached read
- $1.25 / 1M tokens
- Cached write
- $2.50 / 1M tokens
- Batch discount
- 50%
- Source
- OpenAI API pricing
- Verified
- Apr 1, 2026 (High)
Capabilities
- Modalities
- textimageaudio→textaudio
- Capabilities
- webSearchaudioInputimageInputaudioOutputbatchSupportpromptCachingfunctionCallingstructuredOutputs
- Strengths
- Balanced multimodal support, Wide ecosystem adoption
- Tradeoffs
- Superseded by GPT-5.4 for complex reasoning, Migration guidance now points at newer families
Official Links
Benchmark Coverage
| Benchmark | Version | Score | Date | Source | Notes |
|---|---|---|---|---|---|
| MMMU | 2025-rolling | 69.8 accuracy | Sep 1, 2025 | OpenAI model guide | Legacy family reference row. |
Release History
| Release | Alias | Lifecycle | Release Date | Deprecation | Shutdown | Summary |
|---|---|---|---|---|---|---|
| GPT-4o | gpt-4o | Deprecated | May 13, 2024 | Nov 20, 2025 | — | Original flagship multimodal family. |
Host Coverage
| Host | Type | Context | Pricing Note | Differences |
|---|---|---|---|---|
| OpenAI API | first-party | 128.0K | Still available for compatibility-sensitive workloads. | Wide SDK and tooling support |
Migration Guidance
Move new production workloads to GPT-5.4 or GPT-4o mini depending on reasoning needs and budget targets.
Replacement models: gpt-5-4, gpt-4o-mini
Breaking changes: Audio and multimodal behavior can differ when moving to newer text-first families.
Change Events
| Date | Type | Title | Description | Source |
|---|---|---|---|---|
| Nov 20, 2025 | deprecated | Flagship status retired | OpenAI shifted flagship positioning from GPT-4o to GPT-5.4. | OpenAI changelog |
Other models from OpenAI
GPT-4.1, GPT-4.1 mini, GPT-4.1 nano, GPT-4o mini, GPT-5.4, GPT-5.4 mini, GPT-5.4 nano