MCP / Models / Vision and OCR
DeepSeek-OCR MCP: read text from images with no API key
DeepSeek-OCR reads the text in a scanned page, screenshot or photo and returns it as text, running on FlyMy.AI GPUs and billed by run time. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.
$ YOUR NEXT RUN
Use DeepSeek-OCR 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/deepseek-ocr.md. Help me connect the FlyMy.AI MCP to this assistant, then run DeepSeek-OCR (flymyai/deepseek-ocr) for this task: Extract the text from this scanned page with DeepSeek-OCR as Markdown.
What DeepSeek-OCR does
DeepSeek-OCR compresses a page image into a small number of vision tokens before decoding the text, which keeps long documents cheap to read. Send image with a prompt that says what to return, for example 'Convert this page to Markdown'; max_new_tokens, temperature, top_p and do_sample control the output.
DeepSeek-OCR inputs
Every input of flymyai/deepseek-ocr as its live schema lists them. Returns generated_text (string).
Ask your agent
Requests to paste as they are, once the FlyMy.AI MCP is connected.
flymyai/deepseek-ocrflymyai/deepseek-ocrflymyai/deepseek-ocrDeepSeek-OCR price
$5.00 per hour of run time, billed per second. Billed per second of run time on RTX4090x1, $5.00 an hour. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.
Call DeepSeek-OCR 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/deepseek-ocr",
"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/deepseek-ocr/predict/async/result/?request_id=<prediction_id>.
curl -X POST https://api.flymy.ai/api/v1/flymyai/deepseek-ocr/predict/async/ \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-F 'prompt=Describe this picture in two sentences.'Questions about DeepSeek-OCR
Do I need a DeepSeek API key for DeepSeek-OCR?
No. DeepSeek-OCR runs on FlyMy.AI GPUs, so you need no DeepSeek key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.
How much does DeepSeek-OCR cost?
$5.00 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 DeepSeek-OCR in Claude Code, Codex or Cursor?
Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Extract the text from this scanned page with DeepSeek-OCR as Markdown." Your agent reads the inputs with get_model_schema and runs flymyai/deepseek-ocr with run_model.
What does DeepSeek-OCR need as input?
DeepSeek-OCR requires prompt; it also takes 5 optional inputs, each listed on this page with its allowed values and default.
Can I call DeepSeek-OCR from my own code?
Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/deepseek-ocr/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.
Go to the source
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.

