three.ws for Grok

Turn a text prompt into a textured, downloadable 3D model (GLB), free. Describe a single object, character, or creature; the studio generates an interactive model you can rotate, view, and download. Optional quality tier (draft, standard, high); high is slower and may fall back to standard under load. Renders inline in an interactive 3D viewer. Use this for a single object or creature from text; for a posable character call forge_avatar, and to change a model you already made call refine_model.

{
  "type": "object",
  "properties": {
    "idempotency_key": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200,
      "description": "Optional retry key. Send the same key again (same caller, same arguments, within 24 hours) and you get the original job back instead of a second generation, so a retry after a timeout cannot burn quota twice. Use a fresh key for each distinct request. A failed attempt is not remembered, so its key can be reused."
    },
    "prompt": {
      "type": "string",
      "minLength": 3,
      "maxLength": 1000,
      "description": "Description of the single object or character to model, e.g. \"a friendly round robot mascot, glossy white plastic\"."
    },
    "tier": {
      "type": "string",
      "enum": [
        "draft",
        "standard",
        "high"
      ],
      "description": "Detail level: draft (fastest), standard (default), or high (best, slower; may fall back to standard under load)."
    }
  },
  "required": [
    "prompt"
  ],
  "additionalProperties": false
}

Generate a textured 3D avatar (GLB) from a text description or a reference image URL. Best for characters and figures. Renders inline in an interactive 3D viewer. Use this for a character that only needs to be viewed; when it must be posed or animated call forge_avatar instead.

{
  "type": "object",
  "properties": {
    "idempotency_key": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200,
      "description": "Optional retry key. Send the same key again (same caller, same arguments, within 24 hours) and you get the original job back instead of a second generation, so a retry after a timeout cannot burn quota twice. Use a fresh key for each distinct request. A failed attempt is not remembered, so its key can be reused."
    },
    "prompt": {
      "type": "string",
      "maxLength": 1000,
      "description": "Description of the avatar to generate."
    },
    "image_url": {
      "type": "string",
      "format": "uri",
      "description": "Optional http(s) URL to a reference image to reconstruct in 3D."
    }
  },
  "additionalProperties": false
}

Generate a textured 3D mesh (GLB) from a text prompt or a reference image URL. In text mode an AI art-director first refines your prompt into an optimized single-subject spec for higher mesh quality. Renders inline in an interactive 3D viewer. Use this for a single object or prop when mesh quality matters most; for characters call text_to_avatar or forge_avatar.

{
  "type": "object",
  "properties": {
    "idempotency_key": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200,
      "description": "Optional retry key. Send the same key again (same caller, same arguments, within 24 hours) and you get the original job back instead of a second generation, so a retry after a timeout cannot burn quota twice. Use a fresh key for each distinct request. A failed attempt is not remembered, so its key can be reused."
    },
    "prompt": {
      "type": "string",
      "maxLength": 1000,
      "description": "Description of the single object to model."
    },
    "image_url": {
      "type": "string",
      "format": "uri",
      "description": "Optional http(s) URL to a reference image to reconstruct directly."
    }
  },
  "additionalProperties": false
}

Auto-rig a static 3D model (GLB) into an animation-ready model: adds a humanoid skeleton and skin weights so it can be posed and animated. Provide the GLB URL of a model (e.g. one generated by the other tools). Renders the rigged result inline in an interactive 3D viewer. Use this when you already have a static model; to generate and rig a character in one step call forge_avatar instead.

{
  "type": "object",
  "properties": {
    "idempotency_key": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200,
      "description": "Optional retry key. Send the same key again (same caller, same arguments, within 24 hours) and you get the original job back instead of a second generation, so a retry after a timeout cannot burn quota twice. Use a fresh key for each distinct request. A failed attempt is not remembered, so its key can be reused."
    },
    "glb_url": {
      "type": "string",
      "format": "uri",
      "description": "http(s) URL to the static GLB mesh to rig."
    }
  },
  "required": [
    "glb_url"
  ],
  "additionalProperties": false
}

Generate a rigged, animation-ready 3D avatar (GLB) from a single text prompt or a reference image, in one step. Generates the mesh, then auto-rigs it with a humanoid skeleton so it is ready to pose and animate. Best for characters; objects are steered to the mesh generator. Renders inline in an interactive 3D viewer. Use this when the user wants a character they can pose or animate.

{
  "type": "object",
  "properties": {
    "idempotency_key": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200,
      "description": "Optional retry key. Send the same key again (same caller, same arguments, within 24 hours) and you get the original job back instead of a second generation, so a retry after a timeout cannot burn quota twice. Use a fresh key for each distinct request. A failed attempt is not remembered, so its key can be reused."
    },
    "prompt": {
      "type": "string",
      "maxLength": 1000,
      "description": "Description of the character/avatar to generate."
    },
    "image_url": {
      "type": "string",
      "format": "uri",
      "description": "Optional http(s) URL to a reference image to reconstruct in 3D."
    },
    "allow_non_humanoid": {
      "type": "boolean",
      "description": "Set true to rig a non-humanoid subject anyway (rigging assumes a humanoid figure)."
    }
  },
  "additionalProperties": false
}

Iterate on a model you already generated: just describe the change in words ("make it metallic", "bigger helmet", "add wings"). The studio re-generates a new version anchored to the previous one, carrying its form and materials forward. Pass the previous model's glb_url and, when you have it, the prompt that made it (parent_prompt) so the change builds on it. Each refinement is recorded as a new version in a lineage you can revert to or branch from, and the returned lineage drives a version strip in the viewer. Renders the new version inline in the interactive 3D viewer. Use this instead of a fresh generation when the user wants to change a model they already have.

{
  "type": "object",
  "properties": {
    "idempotency_key": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200,
      "description": "Optional retry key. Send the same key again (same caller, same arguments, within 24 hours) and you get the original job back instead of a second generation, so a retry after a timeout cannot burn quota twice. Use a fresh key for each distinct request. A failed attempt is not remembered, so its key can be reused."
    },
    "glb_url": {
      "type": "string",
      "format": "uri",
      "description": "http(s) URL of the model to refine (e.g. the glbUrl a previous generation returned)."
    },
    "instruction": {
      "type": "string",
      "minLength": 1,
      "maxLength": 500,
      "description": "The change to make, in plain language: \"make it metallic\", \"bigger helmet\", \"add a cape\"."
    },
    "parent_prompt": {
      "type": "string",
      "maxLength": 1000,
      "description": "Optional: the prompt that produced the model being refined, so the change builds on it instead of starting over."
    },
    "reference_image_url": {
      "type": "string",
      "format": "uri",
      "description": "Optional http(s) image of the current model to anchor the re-generation (image→3D). Omit for text-guided refinement."
    },
    "parent_lineage": {
      "type": "array",
      "description": "Optional: the lineage array from a previous refine_model result, to extend the same version history.",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    },
    "parent_index": {
      "type": "integer",
      "minimum": 0,
      "description": "Optional: branch off an earlier version in parent_lineage (its index) instead of the latest."
    }
  },
  "required": [
    "glb_url",
    "instruction"
  ],
  "additionalProperties": false
}

Check on a 3D generation that returned status "pending" and collect the finished model. Pass the job_id from the pending result. While it is still rendering you get updated timing; call again after the suggested wait. Checking can save the completed model and restart failed work on another provider. When it is done the model renders inline in the interactive 3D viewer. Use this when the user is waiting to see the finished model; for quiet polling on a schedule call get_job instead.

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string",
      "minLength": 8,
      "maxLength": 4096,
      "description": "The job_id (or jobId) a pending generation returned."
    },
    "refine": {
      "type": "object",
      "additionalProperties": true,
      "description": "Optional: the refine object a pending refine_model result carried. Pass it back unchanged so the finished model joins that version history.",
      "properties": {
        "lineage": {
          "type": "array",
          "items": {
            "type": "object",
            "additionalProperties": true
          }
        },
        "instruction": {
          "type": "string",
          "maxLength": 500
        },
        "parentIndex": {
          "type": "integer",
          "minimum": 0
        },
        "refKind": {
          "type": "string",
          "enum": [
            "text",
            "image"
          ]
        }
      }
    }
  },
  "required": [
    "job_id"
  ],
  "additionalProperties": false
}

Machine-readable status of a generation that returned "pending". Returns status (queued, running, done, failed, not_found), progress (0 to 1, null when unknown), eta_seconds, and next_check_seconds while it runs; the asset links (viewer_url, glb_url, poster_png_url, embed_html) when done; and a plain error with a remedy when it failed. Safe to call on a schedule: it never starts work and is not counted against the generation quota. Use this to poll a pending job from code or a loop; call check_job with the same job_id when you want the finished model rendered in the inline viewer.

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string",
      "minLength": 8,
      "maxLength": 4096,
      "description": "The job_id (or jobId) a pending generation returned."
    },
    "refine": {
      "type": "object",
      "additionalProperties": true,
      "description": "Optional: the refine object a pending refine_model result carried, passed back unchanged."
    }
  },
  "required": [
    "job_id"
  ],
  "additionalProperties": false
}

FREE. See a 3D model instead of just linking to it. Renders the GLB from several angles and returns the frames as images you can actually look at, plus its geometry (triangles, materials, textures) and a plain reading of what those numbers mean. Use it to check your own work right after generating: is the subject complete, is the back finished, is anything melted or fused? Then regenerate naming the fault you saw. Works on any public https .glb, not only ones made here.

{
  "type": "object",
  "properties": {
    "glb_url": {
      "type": "string",
      "minLength": 12,
      "maxLength": 2048,
      "description": "Public https URL of the .glb to look at."
    },
    "views": {
      "type": "array",
      "maxItems": 6,
      "items": {
        "type": "string",
        "enum": [
          "front",
          "three-quarter",
          "side",
          "back",
          "top",
          "bottom"
        ]
      },
      "description": "Angles to render. Default: three-quarter, front, side, back."
    },
    "size": {
      "type": "integer",
      "minimum": 128,
      "maximum": 1024,
      "description": "Pixel size of each square frame. Default 512."
    }
  },
  "required": [
    "glb_url"
  ],
  "additionalProperties": false
}

Free, no account needed. Search every ready-made asset three.ws publishes in one call: CC0 3D props and objects, rigged humanoid characters, and retargetable motion clips. Returns ids, titles, tags, licenses, and CDN urls, plus category facets to narrow the next query. Use this before generating anything: if the catalog already has the prop or character, dropping it in is instant and free where generating one is not. Feed a returned id to get_item_source for code that renders it on any site.

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "maxLength": 200,
      "description": "Free text over titles, names, tags, and categories, e.g. \"wooden chair\", \"office\", \"wave\". Every word must match somewhere, so start broad."
    },
    "kind": {
      "type": "string",
      "enum": [
        "object",
        "character",
        "animation"
      ],
      "description": "Narrow to one library: object (CC0 props), character (rigged humanoids), animation (motion clips)."
    },
    "category": {
      "type": "string",
      "maxLength": 80,
      "description": "Exact category from a previous result's facets."
    },
    "tag": {
      "type": "string",
      "maxLength": 80,
      "description": "Exact tag from a previous result's facets."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 12
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "default": 0,
      "description": "Page offset. Use next_offset from the previous response."
    }
  },
  "additionalProperties": false
}

Free, no account needed. Read one three.ws catalog item in full by its id from search_catalog (for example "object:adjustable_wrench"): metadata, license, CDN urls, the site links that preview or edit it, related items of the same kind, and which source frameworks get_item_source can emit for it. Use this after search_catalog to inspect one result before you embed it; for paste-ready code call get_item_source instead.

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "maxLength": 200,
      "description": "Catalog id as `<kind>:<name>` from search_catalog. A bare name is also accepted."
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false
}

Free, no account needed. Returns working code that renders one three.ws catalog item on any site: the <agent-3d> web component (pinned to the exact published version with its SRI hash), the <model-viewer> tag our own browse grids use, plain three.js with GLTFLoader, or a React component. Motion clips return three.js code that parses the clip JSON and plays it. Omit `framework` to get the one that fits the item best; pass `all` to get every variant at once. Use this when you are ready to put a catalog item on a page or in an app; call get_catalog_item first if you still need its license or metadata.

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "maxLength": 200,
      "description": "Catalog id from search_catalog."
    },
    "framework": {
      "type": "string",
      "enum": [
        "agent-3d",
        "model-viewer",
        "three",
        "react",
        "all"
      ],
      "description": "Which form to emit. Defaults to the recommended one for the item kind. \"all\" returns every applicable variant."
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false
}

Turn a generated GLB into a NAMED, persistent agent body: a "persona" the assistant reuses across turns and across sessions. The model is copied into durable storage so the body survives the source URL expiring, then registered under a stable persona_id. The returned view renders the LIVING body inline: it idles between turns, and persona_say makes it lip-sync and emote a reply. The persona_id is the handle: keep it and pass it to get_agent_persona or persona_say later to bring the exact same body back. Use this once a rigged model should become a recurring character the assistant speaks through. No sign-in required.

{
  "type": "object",
  "properties": {
    "glb_url": {
      "type": "string",
      "format": "uri",
      "description": "Public https URL of the rigged GLB to embody (e.g. from forge_avatar)."
    },
    "name": {
      "type": "string",
      "minLength": 1,
      "maxLength": 80,
      "description": "A display name for the persona, 1–80 characters."
    },
    "voice": {
      "type": "string",
      "maxLength": 64,
      "description": "Optional voice name to speak with (used for audio-driven lip-sync when available)."
    },
    "source_prompt": {
      "type": "string",
      "maxLength": 1000,
      "description": "Optional: the prompt that generated this body, kept as provenance."
    }
  },
  "required": [
    "glb_url",
    "name"
  ],
  "additionalProperties": false
}

Bring back a previously saved persona by its persona_id: the SAME body and identity, in a fresh session. Returns the persona name, its model, the accumulated turn count, and the inline living-body view. Use this when a conversation starts and the user returns to a named agent.

{
  "type": "object",
  "properties": {
    "persona_id": {
      "type": "string",
      "minLength": 8,
      "maxLength": 64,
      "description": "The persona_id returned by create_agent_persona."
    }
  },
  "required": [
    "persona_id"
  ],
  "additionalProperties": false
}

Make a persona PERFORM a reply: the body lip-syncs the text and shows the matching facial expression and body gesture. Pass the persona_id and the exact text the agent is saying this turn; the emotion is detected from the text automatically (or set it explicitly). The returned view animates the body for this turn: show it alongside the reply. Use this whenever the persona speaks, on every turn, with the persona_id from create_agent_persona or get_agent_persona.

{
  "type": "object",
  "properties": {
    "persona_id": {
      "type": "string",
      "minLength": 8,
      "maxLength": 64,
      "description": "The persona to speak through."
    },
    "text": {
      "type": "string",
      "minLength": 1,
      "maxLength": 2000,
      "description": "The reply text the agent is saying this turn: drives lip-sync and emotion."
    },
    "emotion": {
      "type": "string",
      "enum": [
        "neutral",
        "joy",
        "sad",
        "angry",
        "surprised",
        "thinking"
      ],
      "description": "Optional explicit emotion override; omit to auto-detect from the text."
    }
  },
  "required": [
    "persona_id",
    "text"
  ],
  "additionalProperties": false
}