# GPT-3.5 Turbo Instruct API prices

GPT-3.5 Turbo Instruct (gpt) — 4k context, 4k max output.
3 metered per-token offers from 3 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Poe | $1.4 | $1.8 | — | 4k |
| Kilo Gateway | $1.5 | $2 | — | 4k |
| OpenRouter | $1.5 | $2 | — | 4k |

## Summary

- Cheapest input: $1.4 per 1M tokens (Poe)
- Cheapest output: $1.8 per 1M tokens (Poe)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2023-09-28
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-3.5 Turbo Instruct API?

As of Oct 4, 2026, Poe has the lowest GPT-3.5 Turbo Instruct output price at $1.8 per 1M tokens, and Poe has the lowest input price at $1.4 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer GPT-3.5 Turbo Instruct?

3 providers list GPT-3.5 Turbo Instruct on Sovyron; 3 of them sell it at a metered per-token price.

### Is GPT-3.5 Turbo Instruct free?

No provider in the Sovyron catalog lists a free tier for GPT-3.5 Turbo Instruct.

### What is the context window of GPT-3.5 Turbo Instruct?

GPT-3.5 Turbo Instruct supports a 4k-token context window and up to 4k output tokens.

HTML page: https://sovyron.com/models/gpt-3-5-turbo-instruct/
Full dataset: https://sovyron.com/data/catalog.json