Agent
An agent's full record, as returned by `GET /v1/agent/{code}` and `GET /v1/agent/status/{agent_id}`. Every field below is present on every response; fields that do not apply to the agent are `null` rather than absent. `GET /v1/agents` returns a shorter summary — see `AgentListItem`.
Properties
| Name | Type | Description |
|---|---|---|
| code | string | The agent's short code — the primary identifier used across the platform and the embed/viewer URLs. |
| agent_id | string | The same value as `code`, under the name the creation response uses. |
| name | stringnull | The agent's display name. **Generated** from the prompt and portrait during the `persona` step — it cannot be supplied at creation or changed afterwards, and it is `null` until that step completes. |
| description | stringnull | Generated one-paragraph description of the agent. `null` until the `persona` step completes. |
| language | stringnull | Detected/assigned language tag, e.g. `en`. |
| gender | stringnull | |
| model | stringnull | The model family the agent was created with. |
| supported_models | array | Canonical model families this agent can be launched as right now — `essence-1` when its `.imx` exists, and `essence-2` / `expression-2` once their trained per-identity model has been generated. Tier s |
| model_status | object | Readiness per model family, keyed by family name. A family is listed here before it is launchable, with the reason it is not — so a caller can tell "still training" from "never requested". `supported_ |
| subject | stringnull | The subject class the creation classifier recorded for the input, when one was run. |
| system_prompt | stringnull | |
| image_url | stringnull | Avatar face image URL. |
| image_path | stringnull | The stored location of the portrait. Same value as `image_url` for agents whose portrait is public. |
| video_url | stringnull | The agent's identity video URL — generated internally at creation (10 seconds, authored to loop without a seam). Read-only output; video is never a creation input. |
| video_path | stringnull | The stored location of the identity video. Same value as `video_url` for agents whose video is public. |
| model_url | stringnull | Where the model artifact lives. For `essence-1` this is a fetchable URL; for the second-generation families it is an opaque stored handle, **not** a link you can download. Use [the download endpoint]( |
| model_path | stringnull | The same stored handle as `model_url`, under its storage-side name. |
| model_hash | stringnull | Content digest of the model artifact, when one has been recorded. |
| voice_id | stringnull | Voice identifier. |
| voice_path | stringnull | The same value as `voice_id`, under its storage-side name. |
| status | string | Current agent state — `processing`, `generating`, `completed`, `success` (all intermediate), `ready` (terminal success) or `failed` (terminal error). `deleted` for a deleted agent. Stop on `ready` or |
| final | boolean | Coming: not sent yet. When it is, `true` only when `status` is `ready` or `failed` (stop polling) and `false` for every other value, including `success`. Until then, stop on `ready` or `failed`. |
| event_type | stringnull | Most recent pipeline event, e.g. `persona_created`, `voice_created`, `video_created`, `lip_created`. |
| progress | numbernull | Generation progress as a fraction from 0.0 to 1.0. |
| progress_msg | stringnull | Human-readable progress description. |
| current_step | stringnull | Current generation step. Known values: `payment`, `persona`, `voice_image`, `video`, `awaiting_face_marking`, `lip_sync`, `done`. |
| error_message | stringnull | Error details when `status` is `failed`; `null` otherwise. |
| error_type | stringnull | Which stage the failure came from; `null` when the agent has not failed. |
| created_at | string | |
| updated_at | string | |
| dynamics | objectnull | Gesture configuration and available gestures. `{}` when none are configured. |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/bithuman-ai/json-schema/bithuman-ai-agent-schema.json",
"title": "Agent",
"description": "An agent's full record, as returned by `GET /v1/agent/{code}` and `GET /v1/agent/status/{agent_id}`. Every field below is present on every response; fields that do not apply to the agent are `null` rather than absent. `GET /v1/agents` returns a shorter summary — see `AgentListItem`.",
"x-generated": "2026-10-29",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/bithuman-ai-openapi.yaml#/components/schemas/Agent",
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "The agent's short code — the primary identifier used across the platform and the embed/viewer URLs."
},
"agent_id": {
"type": "string",
"description": "The same value as `code`, under the name the creation response uses."
},
"name": {
"type": [
"string",
"null"
],
"description": "The agent's display name. **Generated** from the prompt and portrait during the `persona` step — it cannot be supplied at creation or changed afterwards, and it is `null` until that step completes."
},
"description": {
"type": [
"string",
"null"
],
"description": "Generated one-paragraph description of the agent. `null` until the `persona` step completes."
},
"language": {
"type": [
"string",
"null"
],
"description": "Detected/assigned language tag, e.g. `en`."
},
"gender": {
"type": [
"string",
"null"
]
},
"model": {
"type": [
"string",
"null"
],
"description": "The model family the agent was created with."
},
"supported_models": {
"type": "array",
"items": {
"type": "string"
},
"description": "Canonical model families this agent can be launched as right now — `essence-1` when its `.imx` exists, and `essence-2` / `expression-2` once their trained per-identity model has been generated. Tier slugs inherit their family and are not listed."
},
"model_status": {
"type": "object",
"description": "Readiness per model family, keyed by family name. A family is listed here before it is launchable, with the reason it is not — so a caller can tell \"still training\" from \"never requested\". `supported_models` is the `ready` subset of these keys.",
"additionalProperties": {
"$ref": "#/$defs/ModelStatusEntry"
}
},
"subject": {
"type": [
"string",
"null"
],
"description": "The subject class the creation classifier recorded for the input, when one was run."
},
"system_prompt": {
"type": [
"string",
"null"
]
},
"image_url": {
"type": [
"string",
"null"
],
"description": "Avatar face image URL."
},
"image_path": {
"type": [
"string",
"null"
],
"description": "The stored location of the portrait. Same value as `image_url` for agents whose portrait is public."
},
"video_url": {
"type": [
"string",
"null"
],
"description": "The agent's identity video URL — generated internally at creation (10 seconds, authored to loop without a seam). Read-only output; video is never a creation input."
},
"video_path": {
"type": [
"string",
"null"
],
"description": "The stored location of the identity video. Same value as `video_url` for agents whose video is public."
},
"model_url": {
"type": [
"string",
"null"
],
"description": "Where the model artifact lives. For `essence-1` this is a fetchable URL; for the second-generation families it is an opaque stored handle, **not** a link you can download. Use [the download endpoint](#operation/downloadAgentModel) to get the file itself."
},
"model_path": {
"type": [
"string",
"null"
],
"description": "The same stored handle as `model_url`, under its storage-side name."
},
"model_hash": {
"type": [
"string",
"null"
],
"description": "Content digest of the model artifact, when one has been recorded."
},
"voice_id": {
"type": [
"string",
"null"
],
"description": "Voice identifier."
},
"voice_path": {
"type": [
"string",
"null"
],
"description": "The same value as `voice_id`, under its storage-side name."
},
"status": {
"type": "string",
"description": "Current agent state — `processing`, `generating`, `completed`, `success` (all intermediate), `ready` (terminal success) or `failed` (terminal error). `deleted` for a deleted agent. Stop on `ready` or `failed`; a `final` field is coming."
},
"final": {
"type": "boolean",
"description": "Coming: not sent yet. When it is, `true` only when `status` is `ready` or `failed` (stop polling) and `false` for every other value, including `success`. Until then, stop on `ready` or `failed`."
},
"event_type": {
"type": [
"string",
"null"
],
"description": "Most recent pipeline event, e.g. `persona_created`, `voice_created`, `video_created`, `lip_created`."
},
"progress": {
"type": [
"number",
"null"
],
"format": "float",
"minimum": 0,
"maximum": 1,
"description": "Generation progress as a fraction from 0.0 to 1.0."
},
"progress_msg": {
"type": [
"string",
"null"
],
"description": "Human-readable progress description."
},
"current_step": {
"type": [
"string",
"null"
],
"description": "Current generation step. Known values: `payment`, `persona`, `voice_image`, `video`, `awaiting_face_marking`, `lip_sync`, `done`."
},
"error_message": {
"type": [
"string",
"null"
],
"description": "Error details when `status` is `failed`; `null` otherwise."
},
"error_type": {
"type": [
"string",
"null"
],
"description": "Which stage the failure came from; `null` when the agent has not failed."
},
"created_at": {
"type": "string",
"format": "date-time"
},
"updated_at": {
"type": "string",
"format": "date-time"
},
"dynamics": {
"type": [
"object",
"null"
],
"description": "Gesture configuration and available gestures. `{}` when none are configured."
}
},
"$defs": {
"ModelStatusEntry": {
"type": "object",
"description": "Per-family readiness for one of the agent's models.",
"properties": {
"state": {
"type": "string",
"description": "`ready` when the agent can be launched as this family, `pending` while it is still being prepared."
},
"reason": {
"type": [
"string",
"null"
],
"description": "Why the family is not ready yet; `null` once it is."
},
"updated_at": {
"type": [
"string",
"null"
],
"format": "date-time",
"description": "When this family last changed state. `null` for a family that was available from the agent's creation and never transitioned."
},
"planes": {
"type": "object",
"description": "Readiness for each place the agent runs, present only on the `essence-2` entry of an Essence 2 agent on the current engine. Absent (never `null`) for every other agent and model. `cloud` is the agent's state in the bitHuman cloud; `device` is the state of the copy for your own devices (the Swift, Android and Python SDKs, the CLI and the browser's `render=local`).",
"properties": {
"cloud": {
"type": "string",
"enum": [
"pending",
"ready",
"failed"
],
"description": "The agent's state in the bitHuman cloud; the same value as `state`."
},
"device": {
"type": "string",
"enum": [
"absent",
"preparing",
"ready",
"failed"
],
"description": "`absent` not built yet; `preparing` requested or building; `ready` built and downloadable; `failed` the build stopped."
}
}
}
}
}
}
}
Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
curl "https://apis.io/api/v1/json-schemas/bithuman-ai-agent"
curl "https://apis.io/api/v1/json-schemas?limit=25"
Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.