AgentCompute

Create a private 24-hour trial token automatically. No ChatGPT account, payment or manual setup. Audio: 3 jobs per session. Chat/images: 24 total submissions per rolling 24 hours, 10 per session/reported client, one active task per session, shared queue of 3. Global access issuance caps apply. Retain the token for upload and result retrieval. Reuse the session; never create new sessions to bypass quotas.

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

Check whether the GPU provider can accept audio transcription work. Returns availability, permitted task types, and limits. Does not start a job.

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

Beta users must supply their uploaded asset_id and kind compute_job. No accuracy guarantee is made for uploaded files. Owner legacy calls can queue the fixed synthetic benchmark. compute_job returns a transcript; delegated_task additionally requires word error rate at most 10% against the known reference. Returns a job_id to poll with get_compute_job. No payment is charged. Reuse the same idempotency_key for retries, and use a new key only for a new job.

{
  "type": "object",
  "properties": {
    "access_token": {
      "type": "string",
      "description": "Temporary token returned by create_trial_access. Optional when Bearer authentication is configured."
    },
    "asset_id": {
      "type": "string",
      "description": "Owned upload ID returned by POST /v1/beta/upload. Required for public beta buyers."
    },
    "kind": {
      "type": "string",
      "enum": [
        "compute_job",
        "delegated_task"
      ],
      "description": "Transcription only, or transcription with the reference quality gate."
    },
    "idempotency_key": {
      "type": "string",
      "minLength": 8,
      "maxLength": 100,
      "pattern": "^[A-Za-z0-9_-]{8,100}$",
      "description": "Unique request key. Keep it unchanged on retries."
    }
  },
  "required": [
    "kind",
    "idempotency_key"
  ],
  "additionalProperties": false
}

Read a previously submitted job by job_id. Returns status, transcript, runtime and reference quality when complete. For queued or running jobs, wait poll_after_seconds before checking again. Failed or expired jobs are not successful results.

{
  "type": "object",
  "properties": {
    "access_token": {
      "type": "string",
      "description": "Temporary trial token, unless Bearer authentication is configured."
    },
    "job_id": {
      "type": "string",
      "pattern": "^job_[a-f0-9]{32}$",
      "description": "Exact job_id returned by submit_compute_job."
    }
  },
  "required": [
    "job_id"
  ],
  "additionalProperties": false
}

Public live availability, model catalog, free-trial limits and polling guidance. No token required. Check before submitting; an offline GPU cannot execute work.

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

Queue a free text task: draft, summarize, extract, translate text, reason or assist with code. No code is executed. Provide user/assistant messages, explicit consent for nonconfidential permitted content, and a stable idempotency key. Returns immediately with a job ID. Poll get_studio_job. Uses the configured local model, no external AI fallback.

{
  "type": "object",
  "properties": {
    "access_token": {
      "type": "string",
      "description": "Private token from create_trial_access; optional with Bearer authentication."
    },
    "messages": {
      "type": "array",
      "minItems": 1,
      "maxItems": 16,
      "description": "At most 12,000 characters in total. End with a user message. Include previous messages for follow-up context.",
      "items": {
        "type": "object",
        "properties": {
          "role": {
            "type": "string",
            "enum": [
              "user",
              "assistant"
            ]
          },
          "content": {
            "type": "string",
            "minLength": 1,
            "maxLength": 12000
          }
        },
        "required": [
          "role",
          "content"
        ],
        "additionalProperties": false
      }
    },
    "consent": {
      "type": "boolean",
      "const": true,
      "description": "Confirm permission to process this nonconfidential content."
    },
    "idempotency_key": {
      "type": "string",
      "minLength": 8,
      "maxLength": 100,
      "pattern": "^[A-Za-z0-9_-]{8,100}$"
    }
  },
  "required": [
    "messages",
    "consent",
    "idempotency_key"
  ],
  "additionalProperties": false
}

Queue a free text-to-image task from a complete scene description. Each task is independent, not an edit of a previous image. Returns a job ID; poll get_studio_job then get_studio_image for the PNG. Configured model and size appear in service status/results. No external AI fallback.

{
  "type": "object",
  "properties": {
    "access_token": {
      "type": "string",
      "description": "Private token from create_trial_access; optional with Bearer authentication."
    },
    "prompt": {
      "type": "string",
      "minLength": 3,
      "maxLength": 1200,
      "description": "Complete image description. English prompts are recommended."
    },
    "consent": {
      "type": "boolean",
      "const": true,
      "description": "Confirm permission to process this nonconfidential content."
    },
    "idempotency_key": {
      "type": "string",
      "minLength": 8,
      "maxLength": 100,
      "pattern": "^[A-Za-z0-9_-]{8,100}$"
    }
  },
  "required": [
    "prompt",
    "consent",
    "idempotency_key"
  ],
  "additionalProperties": false
}

Read your own chat/image job. Includes partial text while running, final text or image availability, GPU runtime and server timings. Wait poll_after_seconds between checks; stop on succeeded, failed or expired. Does not create or retry work.

{
  "type": "object",
  "properties": {
    "access_token": {
      "type": "string"
    },
    "job_id": {
      "type": "string",
      "pattern": "^studio_[a-f0-9]{32}$"
    }
  },
  "required": [
    "job_id"
  ],
  "additionalProperties": false
}

Return the completed image as an MCP image content block. Requires the same token/identity that submitted the job. Images expire after 24 hours from submission; download before expiry.

{
  "type": "object",
  "properties": {
    "access_token": {
      "type": "string"
    },
    "job_id": {
      "type": "string",
      "pattern": "^studio_[a-f0-9]{32}$"
    }
  },
  "required": [
    "job_id"
  ],
  "additionalProperties": false
}