token.app › OpenAI › GPT-3.5 Turbo Instruct

GPT-3.5 Turbo Instruct pricing & benchmarks

GPT-3.5 Turbo Instruct is available from OpenAI at $1.50 per million input tokens and $2.00 per million output tokens ($1.63 blended at 3:1). It accepts up to 4,095 tokens of context. This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.

Pricing
Per million tokens · OpenRouter
Input$1.50
Output$2.00
Blended (3:1)$1.63
Specification
openai/gpt-3.5-turbo-instruct
Context window4K
Max output4K
ReleasedSep 2023
LicenceProprietary
Modalitiesin:text, out:text
No independently-run benchmark scores are published for GPT-3.5 Turbo Instruct yet. We show nothing rather than reprinting an unverified figure.
Compare GPT-3.5 Turbo Instruct
GPT-3.5 Turbo Instruct vs Qwen3.8 Max GPT-3.5 Turbo Instruct vs DeepSeek V4 Flash 0731 GPT-3.5 Turbo Instruct vs Claude Opus 5 GPT-3.5 Turbo Instruct vs Gemini 3.6 Flash GPT-3.5 Turbo Instruct vs Kimi K3 GPT-3.5 Turbo Instruct vs Grok 4.5 GPT-3.5 Turbo Instruct vs Claude Sonnet 5 GPT-3.5 Turbo Instruct vs GLM 5.2
FAQ
How much does GPT-3.5 Turbo Instruct cost?
GPT-3.5 Turbo Instruct costs $1.50 per million input tokens and $2.00 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $1.63 per million tokens.
What is GPT-3.5 Turbo Instruct's context window?
GPT-3.5 Turbo Instruct accepts up to 4,095 tokens of context, and can generate up to 4,096 output tokens.