# Pareto API prices

Pareto — 262k context, 131k max output.
4 metered per-token offers from 4 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Cloudflare AI Gateway | $2.5 | $7.5 | $0.25 | 262k |
| Kilo Gateway | $2.5 | $7.5 | $0.25 | 262k |
| NanoGPT | $2.5 | $7.5 | $0.25 | 262k |
| OpenRouter | $2.5 | $7.5 | $0.25 | 262k |

## Summary

- Cheapest input: $2.5 per 1M tokens (Cloudflare AI Gateway)
- Cheapest output: $7.5 per 1M tokens (Cloudflare AI Gateway)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-09-17
- Inputs: image, text

## FAQ

### What is the cheapest Pareto API?

As of Oct 4, 2026, Cloudflare AI Gateway has the lowest Pareto output price at $7.5 per 1M tokens, and Cloudflare AI Gateway has the lowest input price at $2.5 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Pareto?

4 providers list Pareto on Sovyron; 4 of them sell it at a metered per-token price.

### Is Pareto free?

No provider in the Sovyron catalog lists a free tier for Pareto.

### What is the context window of Pareto?

Pareto supports a 262k-token context window and up to 131k output tokens.

HTML page: https://sovyron.com/models/pareto/
Full dataset: https://sovyron.com/data/catalog.json