WaveSpeedAI

Available

WaveSpeedAI has 1 model tracked on Modelglass across 1 vertical (3D), most recently added 2026-06.

Coverage across verticals

3D 1 model

1 ungraded

Inference aggregator (1,000+ models across image/video/audio/3D) with flat per-generation USD pricing and no subscription. Tracked 3D endpoints: wavespeed-ai/hunyuan-3d-v3.1/{text-to-3d-rapid,image-to-3d-rapid} — the Hunyuan3D 3.1 Rapid variant at a flat $0.0225/generation with "no additional charges for mesh complexity or texture quality". WaveSpeed also lists the older Hunyuan3D v2.x and v3 endpoints ($0.02–$0.40) and does not currently carry a Hunyuan3D 3.1 Pro endpoint. Price read from the model page's README and playground cost estimate in-browser (2026-09-04).

See how WaveSpeedAI's models fit into a cost-aware routing setup

Release cadence

1 model tracked across all verticals. Earliest release 2026-06, most recent 2026-06.

Derived from Modelglass's per-vertical provider registries — image/llm/video/audio's registry/providers/*.yaml records, plus science/coding/agentic/gdpval's benchmark registries, where a provider is identified by the prefix before "/" in each model's model_id rather than a registry record of its own. Where the same company uses a different provider slug or model_id prefix across verticals (e.g. Google DeepMind vs. Google Cloud, or Qwen's "alibaba" model_id prefix in the coding registry vs. its "qwen" provider slug elsewhere), coverage is merged onto a single profile per an explicit, human-reviewed alias list (registry/provider-aliases.yaml) — everything else reflects exact-slug or exact-prefix matches only.