Molmo2 Image Qa API Documentation

Molmo2 Image Qa API Documentation

Playground

Molmo2-4B Image QA: Answer questions about images with support for multi-image comparison (1-2 images). Open-source vision-language model. Ready-to-use REST API, no cold starts, affordable pricing.

Features

Ask questions about images and get intelligent answers with Molmo2 Image QA. This vision-language model analyzes single or multiple images and responds to natural language queries — perfect for image understanding, visual analysis, and automated image-based workflows.

Why It Works Great

• Multi-image support: Analyze and compare multiple images at once.
• Natural language: Ask questions in plain English.
• Visual understanding: Comprehends objects, scenes, text, and relationships.
• Instant answers: Fast processing for real-time applications.
• Ultra-affordable: Just $0.002 per query — 500 queries for $1.
• Versatile analysis: From simple identification to complex reasoning.

Parameters

How to Use

1. Upload image(s) — drag and drop or paste public URLs.
2. Click ”+ Add Item” — to add additional images for comparison.
3. Enter your question — describe what you want to know.
4. Run — click the button to get your answer.

Pricing

Flat rate per query.

Best Use Cases

• Image Analysis — Describe what’s in an image in detail.
• Object Identification — Identify objects, people, or elements.
• Text Extraction — Read and transcribe text visible in images.
• Comparison — Compare multiple images for differences or similarities.
• Quality Assessment — Evaluate image quality or content.
• Data Extraction — Pull structured information from visual content.

Example Questions

• “What objects are in this image?”
• “Describe the scene in detail.”
• “What text is visible in this image?”
• “How do these two images differ?”
• “What is the dominant color in this photo?”
• “Is there a person in this image? What are they doing?”
• “What brand logo is shown?”
• “Count the number of items on the table.”

Pro Tips for Best Results

• Be specific with your questions for more precise answers.
• Upload multiple images to compare or analyze together.
• Use for OCR tasks — the model can read text in images.
• At $0.002 per query, batch processing is extremely cost-effective.
• Combine with other Molmo2 tools for comprehensive image workflows.
• Ask follow-up questions about the same images for deeper analysis.

Notes

• Supports multiple images in a single query.
• If using URLs, ensure they are publicly accessible.
• Processing is near-instant for most queries.
• Works with photos, screenshots, diagrams, and more.

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'
{
  "images": [
    "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
  ],
  "text": "A clear example input"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/molmo2/image-qa" \
  -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