GPT-4 Models by OpenAI
Last refreshed 2026-10-17. Next refresh: weekly.
About
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.
Decision facts
- Best fit
- vision and multimodal workJSON / Tool usestructured outputs
- Capability starting point
- GPT-4 Turbo with 128K context and JSON / Tool use, structured outputs, and multimodal inputs
- Lowest tracked input
- GPT-4 Turbo · $5.00/1M · Replicate API
- Closest related family
- Ember
Archived Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
Keep for legacy integrations; evaluate GPT-6.1 Sol before new work.
Keep for legacy integrations; evaluate GPT-6.1 Sol before new work.
Keep only for existing workloads; choose a current variant for new builds.
Keep for legacy integrations; evaluate GPT-6.1 Sol before new work.
Keep only for existing workloads; choose a current variant for new builds.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| GPT-4 Turbo | Keep for legacy integrations; evaluate GPT-6.1 Sol before new work. | 2024-04 | 128K contextJSON / Tool usestructured outputs | Replaced |
| GPT-4 Turbo Preview | Keep for legacy integrations; evaluate GPT-6.1 Sol before new work. | 2023-11 | 128K contextstructured outputscode execution | Replaced |
| GPT-4 Vision Preview | Keep only for existing workloads; choose a current variant for new builds. | 2023-11 | 128K contextcode executionmultimodal inputs | Archived |
| GPT-4 | Keep for legacy integrations; evaluate GPT-6.1 Sol before new work. | 2023-03 | 8K contextJSON / Tool usestructured outputs | Replaced |
| GPT-4 32k | Keep only for existing workloads; choose a current variant for new builds. | 2023-03 | 32K contextcode executionmultimodal inputs | Archived |
Release Timeline
3 release groupsReplaced By
Keep for legacy integrations; evaluate GPT-6.1 Sol before new work.
Keep for legacy integrations; evaluate GPT-6.1 Sol before new work.
Keep for legacy integrations; evaluate GPT-6.1 Sol before new work.
Specifications(5 models)
| Model | Released | Context | Parameters | Vision | Multimodal | JSON / Tool use | Structured Outputs | Code Exec |
|---|---|---|---|---|---|---|---|---|
| GPT-4 Turbo | 2024-04 | 128K | 1.76T (8x222B MoE)* | Yes | Yes | Yes | Yes | Yes |
| GPT-4 Turbo Preview | 2023-11 | 128K | 1.76T (8x222B MoE)* | Yes | No | No | Yes | Yes |
| GPT-4 Vision Preview | 2023-11 | 128K | 1.76T (8x222B MoE)* | Yes | Yes | No | No | Yes |
| GPT-4 | 2023-03 | 8K | 1.76T (8x222B MoE)* | Yes | Yes | Yes | Yes | Yes |
| GPT-4 32k | 2023-03 | 32K | 1.76T (8x222B MoE)* | Yes | No | No | No | Yes |
Available From(6 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| GPT-4 Turbo | Replicate API | $5 | $15 | Serverless |
| GPT-4 Turbo | OpenAI API | $10 | $30 | Serverless |
| GPT-4 Turbo Preview | OpenAI API | $10 | $30 | Serverless |
| GPT-4 Turbo | Azure OpenAI | $10 | $30 | Serverless |
| GPT-4 Turbo Preview | Azure OpenAI | $10 | $30 | Serverless |
| GPT-4 Vision Preview | Azure OpenAI | $10 | $40 | Serverless |
| GPT-4 Turbo | OpenRouter | $10 | $30 | Serverless |
| GPT-4 Turbo Preview | OpenRouter | $10 | $30 | Serverless |
| GPT-4 Turbo | Vercel AI Gateway | $10 | $30 | Serverless |
| GPT-4 | OpenAI API | $30 | $60 | Serverless |
| GPT-4 | Azure OpenAI | $30 | $60 | Serverless |
| GPT-4 | OpenRouter | $30 | $60 | 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 2 (2407)43
- 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
Models(5)
GPT-4 Turbo
GPT-4 Turbo Preview
GPT-4 Vision Preview
GPT-4
GPT-4 32k





