OpenRouterGPT-3.5 Turbo Instruct model ID, context window & pricing
gpt
Quick facts
Model ID openai/gpt-3.5-turbo-instruct
Source OpenRouter
Context Window 4095
Pricing $1.50 input / $2.00 output per 1M tokens
Capabilities structured output, temperature control
Model overview
GPT-3.5 Turbo Instruct is an AI model from OpenRouter with 4095 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 OpenRouter
Family gpt
Status -
Knowledge Cutoff 2021-09-30
Release Date 2023-09-28
Input Modalities text
Output Modalities text
Context Window 4095
Input Limit -
Output Limit 4096
Tool Calling No
Reasoning No
Structured Output Yes
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 -