GPT-3.5 Turbo
GPT-3.5 Turbo is a text-based AI model by OpenAI. It features a 16K token context window, 97 tok/s output speed, $0.50/1M input tokens pricing. It scores 9.0 on the intelligence index.
Strengths
- +Very affordable pricing ($0.50/1M tokens)
Weaknesses
- -Limited context window (16K)
Benchmarks
Intelligence9.0Coding10.7MathN/A
MMLU-Pro
0.5
GPQA
0.3
Intelligence
9.0
Coding
10.7
Output Speed
97 tok/s
Latency (TTFT)
0.42s
Blended Price
$0.75/M
Pricing per 1M Tokens
| Input (Prompt) | $0.50 |
| Output (Completion) | $1.50 |
| Cache Read | Free |
| Cache Write | Free |
Specifications
| Context Length | 16K |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
Compare GPT-3.5 Turbo with:
Alternatives to GPT-3.5 Turbo
More from OpenAI
Frequently Asked Questions
How much does GPT-3.5 Turbo cost?
GPT-3.5 Turbo costs $0.50/1M input tokens and $1.50/1M output tokens.
What is GPT-3.5 Turbo's context window?
GPT-3.5 Turbo supports a context window of 16K tokens, which is approximately 8 pages of text.
Is GPT-3.5 Turbo good for coding?
GPT-3.5 Turbo has a lower coding score of 10.7. For demanding coding tasks, consider a model with a higher coding benchmark.
How fast is GPT-3.5 Turbo?
GPT-3.5 Turbo generates output at 97 tok/s. Time to first token is 0.42s.
Is there a free version of GPT-3.5 Turbo?
Last updated: