# FLUX.2 Klein 4B API prices

FLUX.2 Klein 4B (flux) — 128k context, 128k max output.
1 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 |
| --- | --- | --- | --- | --- |
| NEAR AI Cloud | $1 | $1 | — | 128k |

## Summary

- Cheapest input: $1 per 1M tokens (NEAR AI Cloud)
- Cheapest output: $1 per 1M tokens (NEAR AI Cloud)
- First-party: not listed separately
- Free offers: Nvidia
- Subscription plans (not per-token): none
- Released: 2026-01-14
- Inputs: image, text

## FAQ

### What is the cheapest FLUX.2 Klein 4B API?

As of Oct 4, 2026, NEAR AI Cloud has the lowest FLUX.2 Klein 4B output price at $1 per 1M tokens, and NEAR AI Cloud has the lowest input price at $1 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer FLUX.2 Klein 4B?

3 providers list FLUX.2 Klein 4B on Sovyron; 1 of them sell it at a metered per-token price.

### Is FLUX.2 Klein 4B free?

1 provider(s) list a free-tier offer: Nvidia. Free tiers usually have rate limits.

### What is the context window of FLUX.2 Klein 4B?

FLUX.2 Klein 4B supports a 128k-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/flux-2-klein-4b/
Full dataset: https://sovyron.com/data/catalog.json