Moondream3 Preview Query

Moondream3 Preview Query

Playground

Moondream3 Query answers natural language questions on images with visual Q&A and optional chain of thought for detailed explanations. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Moondream 3 Query is an advanced vision-language model designed to understand images and answer natural-language questions about them. It combines fast inference, accurate scene understanding, and optional reasoning for visual explanation — ideal for analysis, education, and creative applications.

✨ Key Features

• Visual Q&A Ask questions about any image — people, objects, actions, or scenes — and receive natural language answers.

• Chain-of-Thought Reasoning Enable reasoning mode to let the model explain how it reached its conclusion, useful for analysis and debugging.

• Accurate Visual Understanding Trained on diverse, high-quality image-text datasets for reliable recognition of complex visual contexts.

• Fast and Lightweight Optimized for low latency and efficient inference while maintaining strong reasoning performance.

⚙️ Example Usage

🔹 Basic Query

{
 "image": "https://example.com/photo.jpg",
 "prompt": "What is the person in the image doing?"
}

🔹 Query with Reasoning

{
 "image": "https://example.com/photo.jpg",
 "prompt": "What emotions are visible in this scene?",
 "reasoning": true
}

💡 Best Practices

• Ask clear and specific questions for higher accuracy.
• Enable reasoning mode for tasks that require multi-step or contextual analysis.
• Supported image formats: JPEG, PNG, WebP
• Maximum image size: 10 MB

💰 Pricing

• $0.005 per request
• Volume discounts available — please contact WaveSpeedAI for enterprise or batch pricing.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "reasoning": false
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/moondream3-preview/query" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters