Shap-E
OpenAI's text- and image-to-3D model generating textured meshes and NeRFs.
About
Shap-E is OpenAI's conditional 3D generative model, released in May 2023. Unlike prior text-to-3D systems that produce a single output representation, Shap-E directly generates the parameters of implicit functions that can be rendered as both textured meshes and neural radiance fields (NeRFs).
It runs locally in three modes: text-to-3D, image-to-3D, and encode-model, which re-encodes an existing 3D asset into the latent space. OpenAI released the code, model weights and example notebooks on GitHub, making it one of the few fully open OpenAI models.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 8/10
Scored 8/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 123; Trending score 76/100 from researcher assessment.