whichllm — Browse and compare AI model specs and pricing

Vercel AI Gateway

GPT-3.5 Turbo Instruct model ID, context window & pricing

gpt

Quick facts

Model ID openai/gpt-3.5-turbo-instruct
Source Vercel AI Gateway
Context Window 8192
Pricing $1.50 input / $2.00 output per 1M tokens
Capabilities temperature control

Model overview

GPT-3.5 Turbo Instruct is an AI model from Vercel AI Gateway with 8192 token context window and text input support.

Published pricing is $1.50 input and $2.00 output per 1M tokens.

  • Workloads that use text inputs with text outputs.
Model ID openai/gpt-3.5-turbo-instruct
Provider Vercel AI Gateway
Family gpt
Status -
Knowledge Cutoff 2021-09
Release Date 2023-09-28
Input Modalities text
Output Modalities text
Context Window 8192
Input Limit 4096
Output Limit 4096
Tool Calling No
Reasoning No
Structured Output -
Temperature Control Yes
Open Weights No
Input Cost / 1M tokens $1.50
Output Cost / 1M tokens $2.00
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens -
Cache Write Cost / 1M tokens -