GPT-3.5 Turbo
DeprecatedAn OpenAI model with a 16,385-token context window. On the OpenAI API since March 1, 2023, now deprecated.
Access details: OpenAI API
An alias. The provider can point it at a newer version.
gpt-3.5-turboUpdated Sep 23, 2026
Capabilities & limits
- Context window
- 16,385
- Maximum output
- 4K
- Image input
- Unsupported
- Tool calling
- —
- Structured output
- Unsupported
Pricing
USD / 1M tokens- Input
- $0.50
- Output
- $1.50
Standard rates per million tokens. Discounts and long-context rates, where offered, are on OpenAI's pricing page.
Full rate card 2 rates
All prices in USD.
Standard input
$0.50 per 1M tokens- standard processing
Standard output
$1.50 per 1M tokens- standard processing
No cached-input rate listed. Batch API (gpt-3.5-turbo-0125): $0.25 input / $0.75 output per 1M tokens. Deprecated: shutdown scheduled October 23, 2026 (deprecations page).
Price history
Sep 23, 2026
Input $0.50 per million tokens
Sep 23, 2026
Output $1.50 per million tokens
Technical details
- Parameters
- Not published
- Active parameters
- Not published
- Architecture
- Not published
- Training / knowledge cutoff
- Sep 01, 2021
- Input modalities
- Text
- Output modalities
- Text
From OpenAI
Official announcement ↗Release & lifecycle
- First available
- Mar 1, 2023
- deprecated
- As of Sep 13, 2026