---
title: "Flux API — Variants, pricing & model skill"
url: "https://runapi.ai/models/flux.md"
canonical: "https://runapi.ai/models/flux.md"
locale: "en"
model: "Flux"
provider: "Black Forest Labs"
modality: "image"
variant_count: 3
price_from_cents: 3
---

# Flux API

Flux image generation with Dev, Pro, and 2 Klein, plus single-image editing with Dev and Pro.

**Provider:** Black Forest Labs
**Modality:** Image
**Catalog:** 3 variants

Flux spans high-quality production, efficient iteration, and low-latency generation across three models, with single-image editing available on Dev and Pro.

## Variants

| Version | Variant | Pricing | Billing | URL |
|---|---|---|---|---|
| flux-2-klein | `2-klein` | $0.030 | call | https://runapi.ai/models/flux/2-klein.md |
| flux-dev | `dev` | $0.070 | call | https://runapi.ai/models/flux/dev.md |
| flux-pro | `pro` | $0.100 | call | https://runapi.ai/models/flux/pro.md |


## Install the skill

```sh
npx skills add runapi-ai/flux -g
```

The skill gives your coding tool the model docs, schemas, pricing notes, and setup steps needed to add Flux features to an application.

## Context

The Flux API exposes a image model from Black Forest Labs, accessible through RunAPI with a single API key and per-call billing. Developers call Flux the same way they call any other model in the RunAPI catalog — set the model parameter, submit a request, and receive structured JSON. The model skill packages docs, typed schemas, pricing notes, and setup steps so your coding agent has the right context before you write integration code. Billing is unified across all providers, failed generations are never charged, and results are retrievable by task ID.

## FAQ

### Which variant should I start with?

Pick the cheapest variant that meets your quality bar. Most teams start on the fast variant and graduate to pro for production.

### Is there a free tier?

New accounts get free first calls on every model. After that, pay per call.

### Do you stream results?

Where streaming is available, RunAPI streams end-to-end.

### How are failures billed?

Failed generations are not charged.

### Are outputs cached?

Generated outputs are stored and retrievable by task ID. Inputs are not cached.

### Can I use commercially?

Yes — commercial use is included for every variant unless a model license explicitly restricts it, which is called out on the variant page.

### What about rate limits?

Per-key rate limits scale with usage tier. See pricing page for current limits.

### Where can I report issues?

Open an issue on the public GitHub repo or email support.