Build creative AI applications

Create — Nano Banana 2; Prototype — FLUX.2 [dev]; Refine — GPT Image 2; Upscale — P-Image Upscale. Each row above expands with the model's live pricing, capability chips, and sample outputs.

FLUX.2 [dev] runs on Runware's own optimized compute (the platform's open-weight tier, billed on compute time) — check each model page for weight availability and license terms before self-hosting. The remaining picks are partner-served.

The lowest listed starting price in this stack is P-Image Upscale from $0.005 per 1–4 MP; prices are read live from the catalog and scale with resolution, duration, and quality tier. The Production notes below cover how pricing is measured.

Generation spans $0.0051 per image (FLUX.2 dev at 512x512) to $0.15295 (Nano Banana 2 at 4K). Decide the output resolution per surface first, then pick the model tier; a 4K default quietly multiplies spend.

GPT Image 2 spans $0.006 to $0.211 per 1024x1024 edit depending on quality tier. Route iteration traffic to the low tier and reserve the high tier for export-quality output.

Every price on this page is the model's published rate from the live Runware catalog, using the cheapest listed configuration unless stated otherwise. Prices vary with resolution, duration, quality tier, or token volume, so check the pricing table on each model page before estimating unit economics.

The Runware catalog does not publish per-model latency figures, so this page does not quote end-to-end timings. Where a model's own description commits to speed (for example sub-second generation or realtime streaming), that claim is repeated here. For anything else, benchmark the exact models in the Playground with your own payload sizes before committing to an SLA.

Models are addressed by versioned AIR identifiers, so a workflow pinned to specific model versions keeps producing the same behaviour as new versions ship. Adopt upgrades deliberately by re-running your evaluation set against the new version before switching production traffic.

A blueprint bundles the small set of models you would actually wire together for one production use case, instead of ranking a whole category. Each pick covers one stage of the workflow and links to its model page for full schema, pricing, and examples.

Picks are live models from the Best Text-to-Image (30 models), Best Image Editing (21), and Best Upscaling (7) collections in the Runware catalog, chosen to cover the generate, edit, and upscale stages with one open-weight option. Pricing and capability data come from each model's published metadata.