openai
OpenAI: GPT-3.5 Turbo Instruct API Pricing
OpenAI: GPT-3.5 Turbo Instruct costs $1.50 per 1M input tokens and $2.00 per 1M output tokens. Context window: 4K. Prices verified 2026-08-23 Β· source
Input / 1M tokens
$1.50
Output / 1M tokens
$2.00
Context window
4K
Max output
4K
What would OpenAI: GPT-3.5 Turbo Instruct cost you per month?
| Workload | Requests/mo | Avg tokens (in/out) | Est. monthly cost |
|---|---|---|---|
| Light chatbot | 10,000 | 800 / 400 | $20.00 |
| Coding agent | 5,000 | 8,000 / 2,000 | $80.00 |
| RAG pipeline | 30,000 | 4,000 / 500 | $210.00 |
| Doc summarizer | 2,000 | 20,000 / 1,000 | $64.00 |
Estimates use list prices without prompt caching. Caching can cut input cost by up to 90% on repeated context.
About OpenAI: GPT-3.5 Turbo Instruct
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.
Compare OpenAI: GPT-3.5 Turbo Instruct with
Official resources
- OpenAI: GPT-3.5 Turbo Instruct on OpenRouter β live endpoint, pricing source of record.
- Get an OpenRouter API key β β one key, every model including Instruct. Free credits on signup.
- Shred your current bill β paste a CSV and see if switching saves money.