GPT-3.5 Turbo
The model that launched the ChatGPT API in 2023. Deprecated, kept for legacy traffic only; GPT-4.1 nano is the modern cheap default.
GPT-3.5 Turbo is a efficient AI model from OpenAI. It costs $0.5000 per million input tokens and $1.50 per million output tokens (blended $0.8000/M), with a 16,000-token context window.
RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.
Hand-maintained from OpenAI's published pricing; no check date on record.
- Cheap
- Fast
- Wide tooling support
- Legacy 3.5-turbo integrations
Benchmarks
More from OpenAI
See all 28 →Frequently asked questions
How much does GPT-3.5 Turbo cost?
GPT-3.5 Turbo costs $0.5000 per million input tokens and $1.50 per million output tokens, for a blended reference rate of $0.8000 per million tokens.
What is GPT-3.5 Turbo's context window?
GPT-3.5 Turbo supports up to 16,000 tokens of context in a single request.
What is GPT-3.5 Turbo best for?
GPT-3.5 Turbo is well suited to Cheap, Fast and Wide tooling support.
Who makes GPT-3.5 Turbo?
GPT-3.5 Turbo is developed and served by OpenAI. It was released in Mar 2023.
