GPT-4 Turbo
OpenAI
OpenAI's previous-generation flagship with vision capabilities and large context window. Represents a significant upgrade from base GPT-4 with 3x cheaper input pricing and 2x cheaper output pricing. Features 128K context window (equivalent to 300+ pages) and can generate up to 4,096 tokens per response. Strong performance on reasoning, math, and coding tasks with native vision support for analyzing images.
Strengths
- 128K context window fits 300+ pages of text in a single prompt
- Native vision capabilities for analyzing images, charts, and diagrams
- Strong function calling/tool use for agentic workflows
- 3x cheaper input pricing vs original GPT-4 ($10 vs $30)
- December 2023 knowledge cutoff more recent than GPT-4o
- Generates 31.8 tokens per second for fast responses
Caveats
- 4x more expensive than GPT-4o ($10 vs $2.50 input)
- Lower max output tokens (4K) vs newer models (GPT-5.1: 64K)
- Slower than GPT-4o for equivalent tasks
- Being superseded by GPT-4o and GPT-5 series for most use cases
- Higher latency compared to newer optimized models
- Vendor
- OpenAI
- Context Window
- 128,000 tokens
- Max Output
- 4,096 tokens
- License
- Proprietary
- Release Date
- 2024-04-09
- Training Cutoff
- 2023-12-01
- Modalities
- textimage
| Benchmark | Score | Max |
|---|---|---|
| livebench_coding | 49.0 | 100.0 |
| livebench_language | 44.8 | 100.0 |
| livebench_instruction_following | 71.0 | 100.0 |
Capabilities
Vision
Audio
Video
Tool Use
Resources
Pricing
$10.00 per 1M input tokens, $30.00 per 1M output tokens