GPT-3.5 Turbo (1106)

Overview

GPT-3.5 Turbo (1106) is a dated snapshot of OpenAI's GPT-3.5 Turbo, a legacy GPT model that understands and generates natural language or code. It is optimized for chat and also works for non-chat tasks. Snapshots lock in a specific version of the model, so an integration that targets 1106 keeps the same behavior over time.

GPT-3.5 Turbo (1106) has a context window of 16,385 tokens and can generate up to 4,096 output tokens. It accepts text input and returns text output. Its knowledge cutoff is September 1, 2021.

Capabilities

GPT-3.5 Turbo (1106) reads text and returns text, with a context window of 16,385 tokens and up to 4,096 output tokens per request.

It covers multi-turn chat and non-chat natural language and code tasks, and it is listed by OpenAI next to the other dated GPT-3.5 Turbo snapshots.

Pricing

GPT-3.5 Turbo (1106) is billed per token: $1.00 per 1M input tokens and $2.00 per 1M output tokens. GPT-3.5 Turbo (1106) is available through RealRelay's OpenAI-compatible API.

Use cases

Use GPT-3.5 Turbo (1106) when an existing chat assistant or text pipeline is already tested against this exact snapshot and you want its behavior to stay put.

It also handles non-chat text work such as drafting copy, rewriting messages or generating short code snippets within a 16,385-token window. Up to 4,096 output tokens fit in each reply.