Build realtime generation products

Generate — Z-Image-Turbo; Generate — P-Image; Speak — Inworld Realtime TTS-2; Enhance — Llama 3.1 8B Prompt Enhancer. Each row above expands with the model's live pricing, capability chips, and sample outputs.

Z-Image-Turbo and Llama 3.1 8B Prompt Enhancer run 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.

Z-Image-Turbo and P-Image both commit to sub-second generation in their own catalog descriptions, and Inworld TTS-2 is built for low-latency realtime interaction. The catalog publishes no measured latency figures, so validate against your own regions and payload sizes before promising an SLA.

Llama 3.1 8B Prompt Enhancer is currently the only model in the Best Prompt Enhance collection and ships no published per-call price. Treat it as optional in the hot path until you have verified its cost and added a fallback (for example, passing the raw prompt through).

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 Fastest Image Generation (17 models), Fastest Audio Generation (7), and Best Prompt Enhance (1) collections, selected for explicit realtime or sub-second positioning in their own catalog descriptions.