GPT-3.5 Turbo: Benchmarks, Pricing & Context Window
GPT-3.5 Turbo is a language model from OpenAI, released in March 2023.
The latest GPT-3.5 Turbo model with higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls.
GPT-3.5 Turbo pricing
Providers
GPT-3.5 Turbo starts at $0.500 per million input tokens and $1.50 per million output tokens via Azure. See all 2 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Output $/M | Max Input | Max Output | Latency s | Throughput | Quant | Input | Output |
|---|---|---|---|---|---|---|---|---|---|
 Azure | $0.500 | $1.50 | 16.4K | 4.1K | 0.80 | 90 c/s | — | ||
 OpenAI | $0.500 | $1.50 | 16.4K | 4.1K | 0.96 | 116 c/s | — |
GPT-3.5 Turbo API
API access coming soon
GPT-3.5 Turbo will be available through our gateway shortly.
GPT-3.5 Turbo examples
Recent arena outputs from GPT-3.5 Turbo, picked from the highest-ranked matchups.
GPT-3.5 Turbo license
GPT-3.5 Turbo is released under the Proprietary license, which restricts commercial use, has a knowledge cutoff of September 2021.
- License
- Proprietary
- Non-commercial
- Knowledge cutoff
- September 2021
Proprietary license - usage restrictions apply
FAQ
Common questions about GPT-3.5 Turbo.