GPT-4 Models by OpenAI
5 models2023–2024Up to 128k ctxFrom $5/1M input
Details
ResearcherOpenAI
LicenseProprietary
Commercial useCommercial use: conditional
Models5
Released2023–2024
Max context128k
Capabilities
VisionAll models
Multimodal3 of 5 models
Function Calling2 of 5 models
Tool Use1 of 5 models
Structured Outputs3 of 5 models
Code ExecutionAll models
Links
WebsiteAbout
GPT-4 is a large multimodal model that accepts text or image inputs and outputs text. It can solve complex problems with greater accuracy than any of our previous models, thanks to its extensive general knowledge and advanced reasoning capabilities.
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view4 retired
GPT-4 Vision PreviewCurrent
Use when the workload needs 128k context, code execution, and multimodal inputs.
2023-11128k contextcode executionmultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| GPT-4 Vision Preview | Use when the workload needs 128k context, code execution, and multimodal inputs. | 2023-11 | 128k contextcode executionmultimodal inputs | Current |
Release Timeline
3 release groups2024-04
1 retired
GPT-4 Turbo
Replaced128k contexttool usefunction calling
2023-11
1 current · 1 retired
GPT-4 Turbo Preview
Replaced128k contextstructured outputscode execution
GPT-4 Vision Preview
Current128k contextcode executionmultimodal inputs
Replaced By
Replaced
Keep for legacy integrations; evaluate GPT-4.1 before new work.
Replaced
Keep for legacy integrations; evaluate GPT-4.1 before new work.
Specifications(5 models)
| Model | Released | Context | Parameters | Vision | Multimodal | Fn Calling | Tool Use | Structured Outputs | Code Exec |
|---|---|---|---|---|---|---|---|---|---|
| GPT-4 Vision Preview | 2023-11 | 128k | 1.76T (8x222B MoE)* | Yes | Yes | No | No | No | Yes |
Available From(6 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| GPT-4 Vision Preview | Azure OpenAI | $10 | $40 | Serverless |
Popular comparisons in this family
- GPT-4 vs Hunyuan Hy3 Preview114
- GPT-4 vs GPT-285
- ELYZA Japanese Llama 2 13B vs GPT-446
- GPT-4 Vision Preview vs Mistral Large 243
- GPT-4 vs Nemotron Mini 4B Instruct39
- GPT-4 Turbo Preview vs Nemotron Mini 4B Instruct37
- ELYZA Japanese Llama 2 7B vs GPT-435
- GPT-4 vs Llama 3.1 Swallow 8B Instruct33
- GPT-4 vs Qwen3.5-9B31
- GPT-4 Turbo Preview vs Hunyuan Hy3 Preview28
Frequently Asked Questions
- What is GPT-4 used for?
- GPT-4 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-4 compare to GPT Realtime 2?
- GPT-4 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 realtime voice. GPT-4 has 5 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-4 model should I use?
- For the lowest listed input price, start with GPT-4 Turbo through Replicate API at $5/1M input tokens. For the most capable/latest local choice, evaluate GPT-4 Vision Preview with 128k context and multimodal inputs.
