MultimodalAPI only
GPT-4 Turbo
OpenAI
Updated May 21, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error
Superseded by GPT-4o
Specifications
- Type
- Multimodal
- Access
- API only
- Released
- November 6, 2023
- License
- Proprietary
- Context window
- 128,000 tokens
- Knowledge cutoff
- December 31, 2023
- Output speed
- 100 tok/s
- Latency (TTFT)
- 0.5s
- Input
- Text, Image
- Output
- Text
- API pricing
- $10.00 in · $30.00 out / 1M tokens
Capabilities
Function callingStructured output
Benchmarks
Reasoning
| DROP | 86 |
| GPQA Diamond | 48 |
Coding
| HumanEval | 87.1 |
| LiveCodeBench | 29.1 |
General
| MMLU | 86.5 |
| MMLU-Pro | 69.4 |
| Humanity’s Last Exam | 3.3 |
Our take
A faster, cheaper GPT-4 with a 128K context window and a fresher knowledge cutoff. It was the production workhorse of early 2024 until GPT-4o undercut it on both price and latency.