GPT-3.5 Turbo
OpenAI's GPT-3.5 Turbo is a chat model capable of tasks such as code generation, function calling, and reasoning. It is notable for its large context window of 16,385 tokens, allowing it to process and respond to lengthy inputs.
Input
Output
Context
16K
Max Output
4K
Parameters
20B
Technical Specifications
Model TypeChat
Context Window16,385 tokens
Max Output Tokens4,096 tokens
Parameters20B
Release DateFeb 28, 2023
Training CutoffSep 1, 2021
Licenseproprietary
Open SourceNo
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
29.7%
GPQA
44.1%
MATH 500
46.2%
MMLU Pro
10.7
Coding
3.6
Intelligence
143
Speed (tok/s)
0.585
TTFA (s)
0.585
TTFT (s)
Resources & Links
proprietary, Proprietary - API access only
Estimated GPU Requirements for GPT-3.5 Turbo
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.