GPT-4o Models by OpenAI
11 models2024–2025Up to 128k ctxFrom $0.15/1M input
Details
ResearcherOpenAI
LicenseProprietary
Commercial useCommercial use with conditions
Models11
Released2024–2025
Max context128k
Capabilities
Vision6 of 11 models
Multimodal3 of 11 models
Function Calling1 of 11 models
Tool Use1 of 11 models
Structured Outputs8 of 11 models
Code Execution6 of 11 models
About
GPT-4o is OpenAI's most advanced model to date. This multimodal model handles both text and image inputs while generating text outputs. Matching the intelligence of GPT-4 Turbo, it is remarkably more efficient, delivering text at twice the speed and at half the cost. Additionally, GPT-4o exhibits the highest vision performance and excels in non-English languages compared to previous OpenAI models.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
8 in view3 retired
GPT-4o-mini Search PreviewCurrent
Use when the workload needs 128k context and structured outputs.
2025-02128k contextstructured outputs
GPT-4o Search PreviewCurrent
Use when the workload needs 128k context and structured outputs.
2025-02128k contextstructured outputs
GPT-4o (11-20)Current
Use when the workload needs 128k context, code execution, and multimodal inputs.
2024-11128k contextcode executionmultimodal inputs
GPT-4o (2024-11-20)Current
Use when the workload needs 128k context and structured outputs.
2024-11128k contextstructured outputs
GPT-4o-miniCurrent
Use when the workload needs 128k context, structured outputs, and prompt caching.
2024-07128k contextstructured outputsprompt caching
ChatGPT-4oCurrent
Use when the workload needs 128k context, code execution, and multimodal inputs.
2024-05128k contextcode executionmultimodal inputs
GPT-4oCurrent
Use when the workload needs 128k context, tool use, and function calling.
2024-05128k contexttool usefunction calling
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| GPT-4o-mini Search Preview | Use when the workload needs 128k context and structured outputs. | 2025-02 | 128k contextstructured outputs | Current |
| GPT-4o Search Preview | Use when the workload needs 128k context and structured outputs. | 2025-02 | 128k contextstructured outputs | Current |
| GPT-4o (11-20) | Use when the workload needs 128k context, code execution, and multimodal inputs. | 2024-11 | 128k contextcode executionmultimodal inputs | Current |
| GPT-4o (2024-11-20) | Use when the workload needs 128k context and structured outputs. | 2024-11 | 128k contextstructured outputs | Current |
| GPT-4o Audio | Use when the workload needs 128k context. | 2024-10 | 128k context | Current |
| GPT-4o-mini | Use when the workload needs 128k context, structured outputs, and prompt caching. | 2024-07 | 128k contextstructured outputsprompt caching | Current |
| ChatGPT-4o | Use when the workload needs 128k context, code execution, and multimodal inputs. | 2024-05 | 128k contextcode executionmultimodal inputs | Current |
| GPT-4o | Use when the workload needs 128k context, tool use, and function calling. | 2024-05 | 128k contexttool usefunction calling | Current |
Release Timeline
6 release groups2025-02
2 current
GPT-4o Search Preview
Current128k contextstructured outputs
GPT-4o-mini Search Preview
Current128k contextstructured outputs
2024-11
2 current
GPT-4o (11-20)
Current128k contextcode executionmultimodal inputs
GPT-4o (2024-11-20)
Current128k contextstructured outputs
2024-10
1 current
GPT-4o Audio
Current128k context
2024-08
1 retired
GPT-4o (08-06)
Replaced128k contextstructured outputscode execution
2024-07
1 current · 1 retired
GPT-4o Mini (07-18)
Replaced128k contextstructured outputscode execution
GPT-4o-mini
Current128k contextstructured outputsprompt caching
2024-05
2 current · 1 retired
ChatGPT-4o
Current128k contextcode executionmultimodal inputs
GPT-4o
Current128k contexttool usefunction calling
GPT-4o (05-13)
Replaced128k contextstructured outputscode execution
Replaced By
Replaced
Keep for legacy integrations; evaluate GPT-4o before new work.
Replaced
Keep for legacy integrations; evaluate GPT-4o-mini before new work.
Replaced
Keep for legacy integrations; evaluate GPT-4o before new work.
Specifications(11 models)
| Model | Released | Context | Parameters | Vision | Multimodal | Fn Calling | Tool Use | Structured Outputs | Code Exec |
|---|---|---|---|---|---|---|---|---|---|
| GPT-4o-mini Search Preview | 2025-02 | 128k | — | No | No | No | No | Yes | No |
| GPT-4o Search Preview | 2025-02 | 128k | — | No | No | No | No | Yes | No |
| GPT-4o (11-20) | 2024-11 | 128k | 1.76T (8x222B MoE)* | Yes | No | No | No | No | Yes |
| GPT-4o (2024-11-20) | 2024-11 | 128k | — | No | No | No | No | Yes | No |
| GPT-4o Audio | 2024-10 | 128k | — | No | No | No | No | No | No |
| GPT-4o-mini | 2024-07 | 128k | — | No | No | No | No | Yes | No |
| ChatGPT-4o | 2024-05 | 128k | — | Yes | No | No | No | No | Yes |
| GPT-4o | 2024-05 | 128k | — | Yes | Yes | Yes | Yes | Yes | Yes |
Available From(6 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| GPT-4o-mini | OpenAI API | $0.15 | $0.6 | Serverless |
| GPT-4o-mini | OpenRouter | $0.15 | $0.6 | Serverless |
| GPT-4o-mini Search Preview | OpenRouter | $0.15 | $0.6 | Serverless |
| GPT-4o-mini | Vercel AI Gateway | $0.15 | $0.6 | Serverless |
| GPT-4o-mini Search Preview | Vercel AI Gateway | $0.15 | $0.6 | Serverless |
| GPT-4o | Replicate API | $2.5 | $10 | Serverless |
| GPT-4o Audio | OpenRouter | $2.5 | $10 | Serverless |
| GPT-4o Search Preview | OpenRouter | $2.5 | $10 | Serverless |
| GPT-4o (2024-11-20) | OpenRouter | $2.5 | $10 | Serverless |
| GPT-4o | OpenRouter | $2.5 | $10 | Serverless |
| GPT-4o | OpenAI API | $2.5 | $10 | Serverless |
| GPT-4o (2024-11-20) | OpenAI API | $2.5 | $10 | Serverless |
| GPT-4o | Vercel AI Gateway | $2.5 | $10 | Serverless |
Comparisons
- GPT-4o (08-06) vs Claude Sonnet 4.6
- GPT-4o (08-06) vs Claude Opus 4.6
- GPT-4o (08-06) vs Claude 3.5 Sonnet
- GPT-4o (08-06) vs Claude 3.7 Sonnet
- GPT-4o (08-06) vs Gemini 2.5 Pro
- GPT-4o Mini (07-18) vs Gemini 2.5 Flash
- GPT-4o (08-06) vs DeepSeek V4 Pro
- GPT-4o (08-06) vs DeepSeek R1
Frequently Asked Questions
- What is GPT-4o used for?
- GPT-4o is used for vision and multimodal work, agent workflows and tool use, and structured outputs. The family description and listed model capabilities point to those workloads as the best fit.
- How does GPT-4o compare to GPT Realtime 2?
- GPT-4o by OpenAI is strongest where you need vision and multimodal work, while GPT Realtime 2 by OpenAI is the closest related family to check for translation. GPT-4o has 11 listed variants and reaches up to 128k context, while GPT Realtime 2 reaches up to 131k context, so compare the specs and pricing tables before choosing a production model.
- Which GPT-4o model should I use?
- For the lowest listed input price, start with GPT-4o Mini (07-18) through OpenAI API at $0.15/1M input tokens. For the most capable/latest local choice, evaluate GPT-4o with 128k context and tool use, function calling, structured outputs, and multimodal inputs.
Related Model Families
Models(11)
GPT-4o-mini Search Preview
2025-02128k2 providers
GPT-4o Search Preview
2025-02128k1 provider
GPT-4o (11-20)
2024-11128k1.76T (8x222B MoE)*
GPT-4o (2024-11-20)
2024-11128k2 providers
GPT-4o Audio
2024-10128k1 provider
GPT-4o-mini
2024-07128k4 providers
ChatGPT-4o
2024-05128k
GPT-4o
2024-05128k5 providers
Multimodal