MCP / Models / Vision and OCR

Qwen3-VL Instruct MCP: answers about images with no API key

Qwen3-VL Instruct is Alibaba's vision-language model: ask about an image and get a text answer, from descriptions to reading charts and documents. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

Use Qwen3-VL InstructInputs and price
No API key$3.00 / hrVision modelAlibabaCommercial use
Qwen3-VL Instruct sample from the FlyMy.AI catalog

$ YOUR NEXT RUN

Claude CodeCodexCursorAny agent

Use Qwen3-VL Instruct in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/qwen3-vl-instruct-async.md. Help me connect the FlyMy.AI MCP to this assistant, then run Qwen3-VL Instruct (flymyai/qwen3-vl-instruct-async) for this task: Read the text on this receipt photo with Qwen3-VL Instruct and return it as JSON.
Open FlyMy.AIDownload brief

What Qwen3-VL Instruct does

Send image and a prompt with your question. Qwen3-VL reasons about what it sees, reads text in the picture and understands layout and spatial relations. max_new_tokens, temperature, top_p and do_sample control the answer. It runs on our GPUs, asynchronously, and is billed by run time.

Qwen3-VL Instruct inputs

Every input of flymyai/qwen3-vl-instruct-async as its live schema lists them. Returns generated_text (string).

InputType, values and default
# image
file optional Allowed: image file, as a URL or upload
# prompt
string required Default: Hey Qwen! What's up?
# max_new_tokens
integer optional
# temperature
number optional
# top_p
number optional
# do_sample
boolean optional Default: true

Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

“Read the text on this receipt photo with Qwen3-VL Instruct and return it as JSON.”runs flymyai/qwen3-vl-instruct-async
“Explain what this chart shows with Qwen3-VL Instruct, with the three main numbers.”runs flymyai/qwen3-vl-instruct-async
“Compare these two product photos with Qwen3-VL Instruct and list the differences.”runs flymyai/qwen3-vl-instruct-async

Qwen3-VL Instruct price

$3.00 per hour of run time, billed per second. Billed per second of run time, $3.00 an hour. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

See usage pricing →

Call Qwen3-VL Instruct from code

The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.

From an agent, through the MCP

The agent calls get_model_schema, then run_model with:

{
  "endpoint_id": "flymyai/qwen3-vl-instruct-async",
  "input": {
    "prompt": "Describe this picture in two sentences."
  }
}

From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. The answer is a prediction_id; read the result at https://api.flymy.ai/api/v1/flymyai/qwen3-vl-instruct-async/predict/async/result/?request_id=<prediction_id>.

curl -X POST https://api.flymy.ai/api/v1/flymyai/qwen3-vl-instruct-async/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Describe this picture in two sentences.'

Questions about Qwen3-VL Instruct

Do I need a Alibaba API key for Qwen3-VL Instruct?

No. Qwen3-VL Instruct runs on FlyMy.AI GPUs, so you need no Alibaba key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

How much does Qwen3-VL Instruct cost?

$3.00 per hour of run time, billed per second. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-09.

How do I use Qwen3-VL Instruct in Claude Code, Codex or Cursor?

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Read the text on this receipt photo with Qwen3-VL Instruct and return it as JSON." Your agent reads the inputs with get_model_schema and runs flymyai/qwen3-vl-instruct-async with run_model.

What does Qwen3-VL Instruct need as input?

Qwen3-VL Instruct requires prompt; it also takes 5 optional inputs, each listed on this page with its allowed values and default.

Can I call Qwen3-VL Instruct from my own code?

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/qwen3-vl-instruct-async/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

Go to the source

Qwen3-VL Instruct in the playground →Model endpoints in the docs →Every model on FlyMy.AI →Every MCP in the catalog →Usage pricing →

From the FlyMy.AI model catalog of 2026-11-09: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.