Direct Query - Archetype AI Documentation

# The canonical archetypeai-swat-demo-direct-query pattern: the entire state
# snapshot is rendered into `query` as natural language, with a strict
# system prompt that enforces JSON output shape. No file uploads.
curl -X POST https://api.u1.archetypeai.app/v0.5/query \
  -H "Authorization: Bearer $ATAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Newton::c2_5_8b_260413b723a9ab",
    "query": "Current plant state:\n- P1 raw intake: NORMAL\n- P3 ultrafiltration: ATTACK (LIT301=800.16, z=1.5)\n\nReturn one JSON card per anomalous stage.",
    "system_prompt": "Return ONLY a JSON array of {origin,target,direction,text} objects.",
    "instruction_prompt": "Return ONLY a JSON array of {origin,target,direction,text} objects.",
    "file_ids": [],
    "max_new_tokens": 700,
    "sanitize_response": false
  }'

# Upload returns { "file_id": "dashboard.png", "file_uid": "fil_..." }.
# Pass the *file_id* (filename) in file_ids — the file_uid (fil_...) is
# rejected as `unsupported_file_type` because the API filters by extension.
curl -X POST https://api.u1.archetypeai.app/v0.5/query \
  -H "Authorization: Bearer $ATAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Newton::c2_5_8b_260413b723a9ab",
    "query": "Describe what you see. Identify any stages flagged as anomalous.",
    "file_ids": ["dashboard.png"],
    "max_new_tokens": 400,
    "sanitize_response": false
  }'

# .json and .txt files have their contents injected into the prompt
# context automatically. Upload first via /v0.5/files (with mime
# `text/plain` — the file extension is what the rest of the pipeline
# checks), then reference by filename.
curl -X POST https://api.u1.archetypeai.app/v0.5/query \
  -H "Authorization: Bearer $ATAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Newton::c2_5_8b_260413b723a9ab",
    "query": "What is the status field and which sensor has the highest value?",
    "file_ids": ["plant_state.json"],
    "max_new_tokens": 250,
    "sanitize_response": false
  }'

# Channel-first window: outer array = N channels, inner arrays = window_size
# values per channel. Response carries one 768-dim embedding per channel,
# at response.response[i].
curl -X POST https://api.u1.archetypeai.app/v0.5/query \
  -H "Authorization: Bearer $ATAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "OmegaEncoder::omega_embeddings_01",
    "query": "",
    "normalize_input": false,
    "events": [
      {
        "type": "data.numeric_array",
        "event_data": {
          "contents": [
            [2.53, 2.52, 2.53, 2.54],
            [574.2, 575.1, 576.0, 577.3]
          ]
        }
      }
    ]
  }'

import os
import requests

api_key = os.environ["ATAI_API_KEY"]

response = requests.post(
    "https://api.u1.archetypeai.app/v0.5/query",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": "Newton::c2_5_8b_260413b723a9ab",
        "query": "Describe what you see in this dashboard.",
        "file_ids": ["dashboard.png"],
        "max_new_tokens": 400,
        "sanitize_response": False,
    },
)

result = response.json()

if response.status_code == 200 and result.get("status") == "completed":
    # The model's text output is at result["response"]["response"][0].
    # For Omega numeric encoders the same path holds an array of
    # per-channel 768-dim embeddings instead of a string.
    print(result["response"]["response"][0])
else:
    print(f"Error ({response.status_code}):", result.get("errors"))

const response = await fetch('https://api.u1.archetypeai.app/v0.5/query', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${process.env.ATAI_API_KEY}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'Newton::c2_5_8b_260413b723a9ab',
    query: 'Describe what you see in this dashboard.',
    file_ids: ['dashboard.png'],
    max_new_tokens: 400,
    sanitize_response: false
  })
});

const result = await response.json();

if (response.ok && result.status === 'completed') {
  // The model's text output is at result.response.response[0].
  // For Omega numeric encoders the same path holds an array of
  // per-channel 768-dim embeddings instead of a string.
  console.log(result.response.response[0]);
} else {
  console.error(`Error (${response.status}):`, result.errors);
}

{
  "query_id": "260519c33f8455cddda9a8",
  "status": "completed",
  "query_timestamp": 1779157948.572,
  "loading_timestamp": 1779157948.608,
  "inference_timestamp": 1779157948.630,
  "response_timestamp": 1779157956.404,
  "query_queue_time_sec": 0.035,
  "inference_time_sec": 7.774,
  "query_response_time_sec": 7.831,
  "gpq_node": "",
  "response": {
    "success": true,
    "response": [
      "The image appears to be a screenshot from a software interface designed for monitoring and analyzing a six-stage water treatment process..."
    ],
    "query": "Describe what you see. Identify any stages flagged as anomalous.",
    "prompt": "Describe what you see. Identify any stages flagged as anomalous.",
    "system": "...",
    "instruction": "...",
    "generation_latency": 7.77,
    "query_gpq_latency": 7.83,
    "query_queue_latency": 0.05,
    "results_timestamp": "20260519_02:32:36",
    "prefetch_stats": { "loading_time": 0.012 }
  }
}

{
  "query_id": "260518ba9e70f220c2dc48",
  "status": "completed",
  "inference_time_sec": 0.35,
  "query_response_time_sec": 0.41,
  "gpq_node": "",
  "response": {
    "success": true,
    "response": [
      [-0.375, 0.607, -0.733, "..."],
      [-0.412, 0.193, -0.886, "..."]
    ]
  }
}

{
  "errors": [
    {
      "code": "missing_parameter",
      "message": "Failed to find key: model",
      "suggestion": "Resubmit your query with the expected parameters.",
      "error_uid": "err-260506a1b2c3d4"
    }
  ]
}

{
  "errors": [
    {
      "code": "invalid_model_version",
      "message": "Failed to validate the model_version: newton-1",
      "suggestion": "Check to ensure the model is mounted and ready.",
      "error_uid": "err-260506b2c3d4e5"
    }
  ]
}

{
  "errors": [
    {
      "code": "unsupported_file_type",
      "message": "Found unsupported file type with file: fil_526q1cy4nj9rrvtkgqe03mz8n6",
      "suggestion": "Supported file types are ['.png', '.jpg', '.jpeg', '.txt', '.json', '.csv', '.mp4']",
      "error_uid": "err-260506c3d4e5f6"
    }
  ]
}

{
  "detail": "Invalid access for key: "
}

{
  "errors": [
    {
      "code": "gpq_capacity_reached",
      "message": "Failed to submit query, GPQ capacity reached!",
      "suggestion": "Try again later when there is more capacity or add more GPUs to the fleet.",
      "error_uid": "err-260506d4e5f6a7"
    }
  ]
}

{
  "errors": [
    {
      "code": "query_timeout",
      "message": "Response timed out after 60.0 seconds for query: 260506a1b2c3d4e5f6",
      "suggestion": "Try again later when there is more capacity or add more GPUs to the fleet.",
      "error_uid": "err-260506e5f6a7b8"
    }
  ]
}

POST

query

# The canonical archetypeai-swat-demo-direct-query pattern: the entire state
# snapshot is rendered into `query` as natural language, with a strict
# system prompt that enforces JSON output shape. No file uploads.
curl -X POST https://api.u1.archetypeai.app/v0.5/query \
  -H "Authorization: Bearer $ATAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Newton::c2_5_8b_260413b723a9ab",
    "query": "Current plant state:\n- P1 raw intake: NORMAL\n- P3 ultrafiltration: ATTACK (LIT301=800.16, z=1.5)\n\nReturn one JSON card per anomalous stage.",
    "system_prompt": "Return ONLY a JSON array of {origin,target,direction,text} objects.",
    "instruction_prompt": "Return ONLY a JSON array of {origin,target,direction,text} objects.",
    "file_ids": [],
    "max_new_tokens": 700,
    "sanitize_response": false
  }'

# Upload returns { "file_id": "dashboard.png", "file_uid": "fil_..." }.
# Pass the *file_id* (filename) in file_ids — the file_uid (fil_...) is
# rejected as `unsupported_file_type` because the API filters by extension.
curl -X POST https://api.u1.archetypeai.app/v0.5/query \
  -H "Authorization: Bearer $ATAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Newton::c2_5_8b_260413b723a9ab",
    "query": "Describe what you see. Identify any stages flagged as anomalous.",
    "file_ids": ["dashboard.png"],
    "max_new_tokens": 400,
    "sanitize_response": false
  }'

# .json and .txt files have their contents injected into the prompt
# context automatically. Upload first via /v0.5/files (with mime
# `text/plain` — the file extension is what the rest of the pipeline
# checks), then reference by filename.
curl -X POST https://api.u1.archetypeai.app/v0.5/query \
  -H "Authorization: Bearer $ATAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Newton::c2_5_8b_260413b723a9ab",
    "query": "What is the status field and which sensor has the highest value?",
    "file_ids": ["plant_state.json"],
    "max_new_tokens": 250,
    "sanitize_response": false
  }'

# Channel-first window: outer array = N channels, inner arrays = window_size
# values per channel. Response carries one 768-dim embedding per channel,
# at response.response[i].
curl -X POST https://api.u1.archetypeai.app/v0.5/query \
  -H "Authorization: Bearer $ATAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "OmegaEncoder::omega_embeddings_01",
    "query": "",
    "normalize_input": false,
    "events": [
      {
        "type": "data.numeric_array",
        "event_data": {
          "contents": [
            [2.53, 2.52, 2.53, 2.54],
            [574.2, 575.1, 576.0, 577.3]
          ]
        }
      }
    ]
  }'

import os
import requests

api_key = os.environ["ATAI_API_KEY"]

response = requests.post(
    "https://api.u1.archetypeai.app/v0.5/query",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": "Newton::c2_5_8b_260413b723a9ab",
        "query": "Describe what you see in this dashboard.",
        "file_ids": ["dashboard.png"],
        "max_new_tokens": 400,
        "sanitize_response": False,
    },
)

result = response.json()

if response.status_code == 200 and result.get("status") == "completed":
    # The model's text output is at result["response"]["response"][0].
    # For Omega numeric encoders the same path holds an array of
    # per-channel 768-dim embeddings instead of a string.
    print(result["response"]["response"][0])
else:
    print(f"Error ({response.status_code}):", result.get("errors"))

const response = await fetch('https://api.u1.archetypeai.app/v0.5/query', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${process.env.ATAI_API_KEY}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'Newton::c2_5_8b_260413b723a9ab',
    query: 'Describe what you see in this dashboard.',
    file_ids: ['dashboard.png'],
    max_new_tokens: 400,
    sanitize_response: false
  })
});

const result = await response.json();

if (response.ok && result.status === 'completed') {
  // The model's text output is at result.response.response[0].
  // For Omega numeric encoders the same path holds an array of
  // per-channel 768-dim embeddings instead of a string.
  console.log(result.response.response[0]);
} else {
  console.error(`Error (${response.status}):`, result.errors);
}

{
  "query_id": "260519c33f8455cddda9a8",
  "status": "completed",
  "query_timestamp": 1779157948.572,
  "loading_timestamp": 1779157948.608,
  "inference_timestamp": 1779157948.630,
  "response_timestamp": 1779157956.404,
  "query_queue_time_sec": 0.035,
  "inference_time_sec": 7.774,
  "query_response_time_sec": 7.831,
  "gpq_node": "",
  "response": {
    "success": true,
    "response": [
      "The image appears to be a screenshot from a software interface designed for monitoring and analyzing a six-stage water treatment process..."
    ],
    "query": "Describe what you see. Identify any stages flagged as anomalous.",
    "prompt": "Describe what you see. Identify any stages flagged as anomalous.",
    "system": "...",
    "instruction": "...",
    "generation_latency": 7.77,
    "query_gpq_latency": 7.83,
    "query_queue_latency": 0.05,
    "results_timestamp": "20260519_02:32:36",
    "prefetch_stats": { "loading_time": 0.012 }
  }
}

{
  "query_id": "260518ba9e70f220c2dc48",
  "status": "completed",
  "inference_time_sec": 0.35,
  "query_response_time_sec": 0.41,
  "gpq_node": "",
  "response": {
    "success": true,
    "response": [
      [-0.375, 0.607, -0.733, "..."],
      [-0.412, 0.193, -0.886, "..."]
    ]
  }
}

{
  "errors": [
    {
      "code": "missing_parameter",
      "message": "Failed to find key: model",
      "suggestion": "Resubmit your query with the expected parameters.",
      "error_uid": "err-260506a1b2c3d4"
    }
  ]
}

{
  "errors": [
    {
      "code": "invalid_model_version",
      "message": "Failed to validate the model_version: newton-1",
      "suggestion": "Check to ensure the model is mounted and ready.",
      "error_uid": "err-260506b2c3d4e5"
    }
  ]
}

{
  "errors": [
    {
      "code": "unsupported_file_type",
      "message": "Found unsupported file type with file: fil_526q1cy4nj9rrvtkgqe03mz8n6",
      "suggestion": "Supported file types are ['.png', '.jpg', '.jpeg', '.txt', '.json', '.csv', '.mp4']",
      "error_uid": "err-260506c3d4e5f6"
    }
  ]
}

{
  "detail": "Invalid access for key: "
}

{
  "errors": [
    {
      "code": "gpq_capacity_reached",
      "message": "Failed to submit query, GPQ capacity reached!",
      "suggestion": "Try again later when there is more capacity or add more GPUs to the fleet.",
      "error_uid": "err-260506d4e5f6a7"
    }
  ]
}

{
  "errors": [
    {
      "code": "query_timeout",
      "message": "Response timed out after 60.0 seconds for query: 260506a1b2c3d4e5f6",
      "suggestion": "Try again later when there is more capacity or add more GPUs to the fleet.",
      "error_uid": "err-260506e5f6a7b8"
    }
  ]
}

This API endpoint is under active development and is subject to change.

Overview

The /query endpoint runs a synchronous query against an Archetype model. The request is enqueued on the GPU Processing Queue (GPQ), routed to a worker node, and the final result is returned in the same HTTP response. A query can be grounded in:

Uploaded files — reference files by ID via file_ids after uploading them through the Files API. Supported file types: .png, .jpg, .jpeg, .txt, .json, .csv, .mp4.
Inline data events — pass payloads directly via events (text, JSON, base64-encoded image, or numeric arrays) without a separate upload step.
Prompt only — neither files nor events.

The model parameter selects what runs against your inputs. Two model families are currently exposed on /query:

Newton C language models (Newton::c2_...) — text reasoning, structured-output generation, image understanding, and (on C 2.6 fusion checkpoints) video understanding. Used in archetypeai-swat-demo-direct-query, archetypeai-earthquake-demo, archetypeai-grid-demo, and the operator-suggestion patterns documented in the newton-query-prompting skill. Examples on this page use Newton::c2_5_8b_260413b723a9ab. For video, use a C 2.6 fusion checkpoint such as Newton::c2_6_8b_fp8_260424d7a55d5e — see the atai-newton-fusion-model skill.
Omega encoders (OmegaEncoder::omega_embeddings_01) — numeric-only. Returns embedding vectors instead of text. Used with data.numeric_array events to feed channel-first sensor windows; the response carries one 768-dim embedding per channel. Pattern documented in the newton-machine-state-direct-query skill.

The exact model identifiers available to your organization may differ — invalid values return 400 invalid_model_version.

Request

string

required

Versioned model identifier such as Newton::c2_5_8b_260413b723a9ab (text + image reasoning) or OmegaEncoder::omega_embeddings_01 (numeric encoder). Validated against the available model registry — invalid values return 400 invalid_model_version. See Overview for the model families currently exposed on this endpoint.

string

required

The natural-language query to run against the model. For numeric-encoder models (Omega) this is typically "" — pass the sensor window as a data.numeric_array event in events instead.

string

default:""

Optional system prompt prepended to the query.

string

default:""

Optional instruction prompt appended to the system prompt.

string

default:""

Optional prefix used to seed the model’s response.

string

default:""

Optional named prompt template to apply server-side.

string[]

File IDs returned by the Files API. Two gotchas worth knowing:

Use the file_id (filename) the upload response returned, not the file_uid (fil_…). /query filters file types by extension on the file_id string — fil_… has no extension and is rejected as unsupported_file_type.
Newton text models see contents of .png / .jpg / .jpeg / .txt / .json injected into the prompt; .csv is the exception. CSV uploads succeed and /query accepts the reference, but the file contents are not visible to the text-reasoning model (likely routed to the numeric ingestion path the LLM doesn’t observe). As a workaround, rename the file to end with .txt before uploading, or pass the CSV contents as a data.text event instead. .mp4 requires a C 2.6 fusion checkpoint such as Newton::c2_6_8b_fp8_260424d7a55d5e — older C 2.4/2.5 text checkpoints do not process video frames. The clip is decoded and uniformly sampled server-side (control this with max_frames); see the atai-newton-fusion-model skill for the full video patterns.

object[]

Inline data events in place of file uploads. See Data Events for the supported event types: data.text, data.json, data.base64_img, data.base64_img_array, data.numeric_array. For data.json, set event_data.contents to a serialized JSON string (passing a parsed object returns 400 invalid_parameter_type).

integer

default:"256"

Maximum tokens to generate in the response.

integer

default:"32"

Maximum video frames to sample when an .mp4 file is supplied via file_ids. The platform maximum is 64 — values above 64 fail silently: the request returns 200 but the video is dropped and the model answers from priors. Video requires a C 2.6 fusion checkpoint (see Overview).

number

Sampling temperature. Omit to use the model default.

boolean

Whether to use sampling instead of greedy decoding.

number

Penalty for repeating tokens already produced.

number

Nucleus sampling cutoff.

integer

Top-k sampling cutoff.

number

Penalty for tokens already present in the prompt.

boolean

default:"false"

Apply server-side input normalization. For numeric-encoder models (Omega), this z-scores each data.numeric_array event per window before encoding. That preserves cross-channel comparability but erases cross-window amplitude signal — typically the wrong default for anomaly-detection workloads. Leave false and pre-normalize with a global scaler if cross-window magnitudes carry meaning. Has no effect on text-reasoning models.

boolean

default:"false"

When true, treat multiple file_ids / image events as a single multi-image input rather than independent inputs.

boolean

default:"false"

When true, retains rendered intermediate artifacts on the server. The retrieval endpoint for these artifacts is not exposed on /v0.5; leave this false unless instructed otherwise.

object

Free-form metadata stored alongside the query for the caller’s own bookkeeping.

number

Override the maximum combined prompt size in MB. Defaults to the server’s MAX_QUERY_SIZE_MB setting (typically 0.04 MB).

number

Override the maximum time to wait for a synchronous result before returning a 504.

boolean

default:"true"

When true, strips internal fields (api_key, org_id, query_metadata, file_ids, data_types, render, input_items, sanitize) from the response. Set to false only if you need to inspect the raw query record.

Response

string

Server-generated identifier for this query. Include it when reporting issues to support so the platform team can correlate to server logs.

string

Terminal status — completed for successful queries, failed if the worker returned an error.

object

Structured payload from the worker. The primary model output is the array at response.response (typically one or more strings). The remaining fields echo the prompt inputs (query, prompt, system, instruction) and per-stage timing (generation_latency, query_gpq_latency, query_queue_latency, results_timestamp, prefetch_stats) for debugging.

number

Unix timestamp when the query was submitted.

number

Unix timestamp when data loading began.

number

Unix timestamp when inference began.

number

Unix timestamp when the response was finalized.

number

Seconds spent in the queue before processing began.

number

Seconds spent on inference.

number

End-to-end latency from submission to response.

string

Identifier of the GPQ worker node that processed the query.

string[]

Plain-string error log accumulated by GPQ during query processing. Only present when GPQ has appended at least one message — successful queries typically omit this field entirely.

string

Single error string set by GPQ only when status is failed.

Non-2xx responses (400, 429, 504) are reduced to an { "errors": [...] } envelope by the shared API response wrapper — fields like query_id, status, and timing data are stripped. 401 responses are rendered as { "detail": "..." } by FastAPI. See Errors for the shared AtaiError shape.

# The canonical archetypeai-swat-demo-direct-query pattern: the entire state
# snapshot is rendered into `query` as natural language, with a strict
# system prompt that enforces JSON output shape. No file uploads.
curl -X POST https://api.u1.archetypeai.app/v0.5/query \
  -H "Authorization: Bearer $ATAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Newton::c2_5_8b_260413b723a9ab",
    "query": "Current plant state:\n- P1 raw intake: NORMAL\n- P3 ultrafiltration: ATTACK (LIT301=800.16, z=1.5)\n\nReturn one JSON card per anomalous stage.",
    "system_prompt": "Return ONLY a JSON array of {origin,target,direction,text} objects.",
    "instruction_prompt": "Return ONLY a JSON array of {origin,target,direction,text} objects.",
    "file_ids": [],
    "max_new_tokens": 700,
    "sanitize_response": false
  }'

# Upload returns { "file_id": "dashboard.png", "file_uid": "fil_..." }.
# Pass the *file_id* (filename) in file_ids — the file_uid (fil_...) is
# rejected as `unsupported_file_type` because the API filters by extension.
curl -X POST https://api.u1.archetypeai.app/v0.5/query \
  -H "Authorization: Bearer $ATAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Newton::c2_5_8b_260413b723a9ab",
    "query": "Describe what you see. Identify any stages flagged as anomalous.",
    "file_ids": ["dashboard.png"],
    "max_new_tokens": 400,
    "sanitize_response": false
  }'

# .json and .txt files have their contents injected into the prompt
# context automatically. Upload first via /v0.5/files (with mime
# `text/plain` — the file extension is what the rest of the pipeline
# checks), then reference by filename.
curl -X POST https://api.u1.archetypeai.app/v0.5/query \
  -H "Authorization: Bearer $ATAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Newton::c2_5_8b_260413b723a9ab",
    "query": "What is the status field and which sensor has the highest value?",
    "file_ids": ["plant_state.json"],
    "max_new_tokens": 250,
    "sanitize_response": false
  }'

# Channel-first window: outer array = N channels, inner arrays = window_size
# values per channel. Response carries one 768-dim embedding per channel,
# at response.response[i].
curl -X POST https://api.u1.archetypeai.app/v0.5/query \
  -H "Authorization: Bearer $ATAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "OmegaEncoder::omega_embeddings_01",
    "query": "",
    "normalize_input": false,
    "events": [
      {
        "type": "data.numeric_array",
        "event_data": {
          "contents": [
            [2.53, 2.52, 2.53, 2.54],
            [574.2, 575.1, 576.0, 577.3]
          ]
        }
      }
    ]
  }'

import os
import requests

api_key = os.environ["ATAI_API_KEY"]

response = requests.post(
    "https://api.u1.archetypeai.app/v0.5/query",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": "Newton::c2_5_8b_260413b723a9ab",
        "query": "Describe what you see in this dashboard.",
        "file_ids": ["dashboard.png"],
        "max_new_tokens": 400,
        "sanitize_response": False,
    },
)

result = response.json()

if response.status_code == 200 and result.get("status") == "completed":
    # The model's text output is at result["response"]["response"][0].
    # For Omega numeric encoders the same path holds an array of
    # per-channel 768-dim embeddings instead of a string.
    print(result["response"]["response"][0])
else:
    print(f"Error ({response.status_code}):", result.get("errors"))

const response = await fetch('https://api.u1.archetypeai.app/v0.5/query', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${process.env.ATAI_API_KEY}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'Newton::c2_5_8b_260413b723a9ab',
    query: 'Describe what you see in this dashboard.',
    file_ids: ['dashboard.png'],
    max_new_tokens: 400,
    sanitize_response: false
  })
});

const result = await response.json();

if (response.ok && result.status === 'completed') {
  // The model's text output is at result.response.response[0].
  // For Omega numeric encoders the same path holds an array of
  // per-channel 768-dim embeddings instead of a string.
  console.log(result.response.response[0]);
} else {
  console.error(`Error (${response.status}):`, result.errors);
}

{
  "query_id": "260519c33f8455cddda9a8",
  "status": "completed",
  "query_timestamp": 1779157948.572,
  "loading_timestamp": 1779157948.608,
  "inference_timestamp": 1779157948.630,
  "response_timestamp": 1779157956.404,
  "query_queue_time_sec": 0.035,
  "inference_time_sec": 7.774,
  "query_response_time_sec": 7.831,
  "gpq_node": "",
  "response": {
    "success": true,
    "response": [
      "The image appears to be a screenshot from a software interface designed for monitoring and analyzing a six-stage water treatment process..."
    ],
    "query": "Describe what you see. Identify any stages flagged as anomalous.",
    "prompt": "Describe what you see. Identify any stages flagged as anomalous.",
    "system": "...",
    "instruction": "...",
    "generation_latency": 7.77,
    "query_gpq_latency": 7.83,
    "query_queue_latency": 0.05,
    "results_timestamp": "20260519_02:32:36",
    "prefetch_stats": { "loading_time": 0.012 }
  }
}

{
  "query_id": "260518ba9e70f220c2dc48",
  "status": "completed",
  "inference_time_sec": 0.35,
  "query_response_time_sec": 0.41,
  "gpq_node": "",
  "response": {
    "success": true,
    "response": [
      [-0.375, 0.607, -0.733, "..."],
      [-0.412, 0.193, -0.886, "..."]
    ]
  }
}

{
  "errors": [
    {
      "code": "missing_parameter",
      "message": "Failed to find key: model",
      "suggestion": "Resubmit your query with the expected parameters.",
      "error_uid": "err-260506a1b2c3d4"
    }
  ]
}

{
  "errors": [
    {
      "code": "invalid_model_version",
      "message": "Failed to validate the model_version: newton-1",
      "suggestion": "Check to ensure the model is mounted and ready.",
      "error_uid": "err-260506b2c3d4e5"
    }
  ]
}

{
  "errors": [
    {
      "code": "unsupported_file_type",
      "message": "Found unsupported file type with file: fil_526q1cy4nj9rrvtkgqe03mz8n6",
      "suggestion": "Supported file types are ['.png', '.jpg', '.jpeg', '.txt', '.json', '.csv', '.mp4']",
      "error_uid": "err-260506c3d4e5f6"
    }
  ]
}

{
  "detail": "Invalid access for key: "
}

{
  "errors": [
    {
      "code": "gpq_capacity_reached",
      "message": "Failed to submit query, GPQ capacity reached!",
      "suggestion": "Try again later when there is more capacity or add more GPUs to the fleet.",
      "error_uid": "err-260506d4e5f6a7"
    }
  ]
}

{
  "errors": [
    {
      "code": "query_timeout",
      "message": "Response timed out after 60.0 seconds for query: 260506a1b2c3d4e5f6",
      "suggestion": "Try again later when there is more capacity or add more GPUs to the fleet.",
      "error_uid": "err-260506e5f6a7b8"
    }
  ]
}

⌘I

​Overview

​Request

​Response

Overview

Request

Response