GPT-4 Turbo
GPT-4 Turbo is a multimodal AI model by OpenAI. It features a 128K token context window, 23 tok/s output speed, $10/1M input tokens pricing. It scores 13.7 on the intelligence index.
Strengths
- +Supports image input (vision)
Weaknesses
- -Slower than average output (23 tok/s)
Benchmarks
Intelligence13.7Coding21.5MathN/A
MMLU-Pro
0.7
LiveCodeBench
0.3
Intelligence
13.7
Coding
21.5
Output Speed
23 tok/s
Latency (TTFT)
1.00s
Blended Price
$15.00/M
Pricing per 1M Tokens
| Input (Prompt) | $10 |
| Output (Completion) | $30 |
| Cache Read | Free |
| Cache Write | Free |
Specifications
| Context Length | 128K |
| Max Output Tokens | N/A |
| Input Modalities | Text + Image |
| Output Modalities | Text |
| Tokenizer | N/A |
Compare GPT-4 Turbo with:
Alternatives to GPT-4 Turbo
More from OpenAI
Frequently Asked Questions
How much does GPT-4 Turbo cost?
GPT-4 Turbo costs $10/1M input tokens and $30/1M output tokens.
What is GPT-4 Turbo's context window?
GPT-4 Turbo supports a context window of 128K tokens, which is approximately 64 pages of text.
Is GPT-4 Turbo good for coding?
GPT-4 Turbo has a lower coding score of 21.5. For demanding coding tasks, consider a model with a higher coding benchmark.
How fast is GPT-4 Turbo?
GPT-4 Turbo generates output at 23 tok/s. Time to first token is 1.00s.
Is there a free version of GPT-4 Turbo?
Last updated: