Seedream 5.0 Pro ya está aquí | Pruébalo en el Generador de Imágenes →

Minicpm V Image

wavespeed-ai /

MiniCPM-V 4.5 is the latest, most capable MiniCPM-V image model for accurate AI image understanding and analysis across visual tasks. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-text
Entrada

Inactivo

This image captures a serene and idyllic scene of a young girl lying in a sunlit field. She is positioned on her back, with her eyes closed as if she's peacefully drifting off to sleep or simply enjoying the warmth of the sunlight filtering through gentle dapples above. Her light brown hair flows softly around her head like golden waves caught by an invisible breeze; some strands drift upwards while others settle gently across one cheek—adding movement without disturbing serenity. Dressed casually yet comfortably for warm weather (though specific details about clothing aren't clear), there’s no sign that anything would disturb this momentary repose: neither shoes nor socks are visible beneath grassy coverings which partially obscure lower limbs but leave enough exposed skin suggesting relaxed posture rather than any strain against nature itself Surrounding them are countless white-petaled flowers known commonly today perhaps more widely referred generically even though botanically distinct types exist among these delicate spheres topped often delicately at their centers—a common feature seen particularly well here where individual seed heads stand out crisply lit from behind creating soft shadows adding depth contrast beautifully contrasting vibrant green blades forming lush carpet underfoot stretching far beyond frame edges into distance softened slightly blurred effect giving sense vastness openness typical pastoral landscapes spring/summer settings evoke feelings peace tranquility connection earth sky

$0.005por ejecución·~200 / $1

Siguiente:

EjemplosVer todo

Modelos relacionados

README

MiniCPM-V Image

MiniCPM-V Image is an efficient AI-powered image understanding model that analyzes and describes images based on your prompts. Upload an image, choose a preset or write a custom prompt, and get detailed descriptions, analysis, or answers about the visual content.

Why It Stands Out

  • Image understanding: Analyzes visual content and provides detailed descriptions.
  • Preset prompts: Quick access to common tasks like "describe" for instant use.
  • Custom prompts: Ask specific questions or request particular analysis.
  • Ultra-affordable: High-quality image understanding at just $0.005 per image.
  • Reproducibility: Use the seed parameter to recreate exact results.

Parameters

ParameterRequiredDescription
imageYesImage to analyze (upload or public URL).
preset_promptNoPreset task: describe, etc. (default: describe).
custom_promptNoCustom question or instruction about the image.
seedNoSet for reproducibility; -1 for random.

How to Use

  1. Upload your image — drag and drop a file or paste a public URL.
  2. Select a preset prompt — choose "describe" or other presets for quick analysis.
  3. Or write a custom prompt — ask specific questions about the image.
  4. Click Run and receive the analysis.

Example Use Cases

Using preset "describe":

  • Get a detailed description of the image content, subjects, and scene.

Using custom prompts:

  • "What objects are in this image?"
  • "Describe the mood and atmosphere of this photo."
  • "What text is visible in this image?"
  • "Count the number of people in this photo."
  • "What is the main subject doing?"

Best Use Cases

  • Image Captioning — Generate descriptions for images in your content.
  • Content Analysis — Understand and categorize visual content at scale.
  • Accessibility — Create alt text and descriptions for visually impaired users.
  • Data Extraction — Extract information from images like text, objects, or scenes.
  • Quality Control — Analyze images for specific attributes or content.

Pricing

OutputPrice
Per image$0.005

Pro Tips for Best Quality

  • Use preset prompts for common tasks like general description.
  • Write specific custom prompts when you need particular information.
  • For OCR-style tasks, ask directly: "What text is in this image?"
  • Combine with other models for workflows like image-to-text-to-video.

Notes

  • Ensure uploaded image URLs are publicly accessible.
  • Processing time varies based on current queue load.
  • Please ensure your content complies with usage guidelines.
Nota:Este sitio web utiliza modelos de IA proporcionados por terceros.

Minicpm V Image API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/minicpm-v/image 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 Minicpm V Image below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "preset_prompt": "describe",
    "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/minicpm-v/image" \
  -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/minicpm-v/image";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "preset_prompt": "describe",
        "seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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 = {
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "preset_prompt": "describe",
    "seed": -1
}

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/minicpm-v/image", 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)

Minicpm V Image API — Frequently asked questions

What is the Minicpm V Image API?

Minicpm V Image is a WaveSpeedAI model for AI inference, exposed as a REST API on WaveSpeedAI. MiniCPM-V 4.5 is the latest, most capable MiniCPM-V image model for accurate AI image understanding and analysis across visual tasks. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Minicpm V Image 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/minicpm-v-image.

How much does Minicpm V Image cost per run?

Minicpm V Image starts at $0.005 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 Minicpm V Image accept?

Key inputs: `image`, `seed`, `custom_prompt`, `enable_sync_mode`, `preset_prompt`. 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/minicpm-v-image.

How long does Minicpm V Image take to generate?

Median end-to-end generation time on WaveSpeedAI is around 95 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 Minicpm V Image 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.

Minicpm V Image | AI Image Understanding API | WaveSpeedAI