# GPT-3.5-turbo API prices

GPT-3.5-turbo (gpt) — 16k context, 4k max output.
11 metered per-token offers from 11 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Poe | $0.45 | $1.4 | — | 16k |
| Eden AI | $0.5 | $1.5 | — | 16k |
| Impossibl | $0.5 | $1.5 | — | 16k |
| Kilo Gateway | $0.5 | $1.5 | — | 16k |
| DevPass (LLM Gateway) | $0.5 | $1.5 | free | 16k |
| LLM Gateway | $0.5 | $1.5 | — | 16k |
| Merge Gateway | $0.5 | $1.5 | — | 16k |
| NanoGPT | $0.5 | $1.5 | — | 16k |
| OpenRouter | $0.5 | $1.5 | — | 16k |
| OrcaRouter | $0.5 | $1.5 | free | 16k |
| Vercel AI Gateway | $0.5 | $1.5 | — | 16k |

## Summary

- Cheapest input: $0.45 per 1M tokens (Poe)
- Cheapest output: $1.4 per 1M tokens (Poe)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2023-03-01
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-3.5-turbo API?

As of Oct 4, 2026, Poe has the lowest GPT-3.5-turbo output price at $1.4 per 1M tokens, and Poe has the lowest input price at $0.45 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?

11 providers list GPT-3.5-turbo on Sovyron; 11 of them sell it at a metered per-token price.

### Is GPT-3.5-turbo free?

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

### What is the context window of GPT-3.5-turbo?

GPT-3.5-turbo supports a 16k-token context window and up to 4k output tokens.

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