Seedance 2.5 Now Live | Try in Video Generator →

wavespeed-ai/

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.

image-to-text
Input

Idle

The decorations are floating because they're in a microgravity environment, which is typical of space. In orbit, objects don't experience the same gravitational pull as on Earth, so anything without a strong force holding it down will float freely. This includes the Christmas ornaments, wreaths, and other festive decorations visible in the space station. The astronauts can place these decorations in the station and they'll remain suspended, creating a unique and whimsical holiday scene against the backdrop of Earth and space.

$0.002per run·~500 / $1

Next:

ExamplesView all

Related Models

README

Molmo2 Image QA

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

ParameterRequiredDescription
imagesYesOne or more images to analyze (upload or public URLs).
textYesYour question or prompt about the image(s).

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.

OutputCost
Per query$0.002
100 queries$0.20
1,000 queries$2.00

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.
Note:This website uses AI models provided by third parties. Documentation prices are for reference and may be outdated. The Generate button shows an estimate; the final task charge prevails.

Molmo2 Image Qa API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/molmo2/image-qa with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Molmo2 Image Qa below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_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 "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; 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' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$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
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/molmo2/image-qa";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "images": [
                "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
        ],
        "text": "A clear example input"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "images": [
        "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
    ],
    "text": "A clear example input"
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/molmo2/image-qa", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Molmo2 Image Qa API — Frequently asked questions

What is the Molmo2 Image Qa API?

Molmo2 Image Qa is a WaveSpeedAI model for AI inference, exposed as a REST API on WaveSpeedAI. 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. You can call it programmatically or try it from the playground above.

How do I call the Molmo2 Image Qa API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/molmo2-image-qa.

How much does Molmo2 Image Qa cost per run?

Molmo2 Image Qa starts at $0.002 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Molmo2 Image Qa accept?

Key inputs: `images`, `enable_sync_mode`, `text`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/molmo2-image-qa.

How long does Molmo2 Image Qa take to generate?

Median end-to-end generation time on WaveSpeedAI is around 7 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Molmo2 Image Qa outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

Molmo2 Image Qa | AI Image Understanding API on WaveSpeedAI