# DeepSeek-OCR MCP and API by DeepSeek | FlyMy.AI

> 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.

Page: https://flymy.ai/mcp/models/deepseek-ocr/

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.

[Use DeepSeek-OCR](https://flymy.ai/mcp/models/deepseek-ocr/#start) [Inputs and price](https://flymy.ai/mcp/models/deepseek-ocr/#inputs)

No API key, $5.00 / hr, OCR, DeepSeek, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## 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.
```

[Open FlyMy.AI](https://app.flymy.ai/new-agent) [Download brief](https://flymy.ai/mcp/models/deepseek-ocr.md)

## 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).

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/deepseek-ocr/#input-image) `image` | file optional Allowed: image file, as a URL or upload |
| [#](https://flymy.ai/mcp/models/deepseek-ocr/#input-prompt) `prompt` | string required |
| [#](https://flymy.ai/mcp/models/deepseek-ocr/#input-max_new_tokens) `max_new_tokens` | integer optional |
| [#](https://flymy.ai/mcp/models/deepseek-ocr/#input-temperature) `temperature` | number optional |
| [#](https://flymy.ai/mcp/models/deepseek-ocr/#input-top_p) `top_p` | number optional |
| [#](https://flymy.ai/mcp/models/deepseek-ocr/#input-do_sample) `do_sample` | boolean optional Default: `true` |

## Ask your agent

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

**“Extract the text from this scanned page with DeepSeek-OCR as Markdown.”** runs `flymyai/deepseek-ocr`

**“Read the table in this screenshot with DeepSeek-OCR and give it back as CSV.”** runs `flymyai/deepseek-ocr`

**“Use DeepSeek-OCR to pull the invoice number, date and total from this photo.”** runs `flymyai/deepseek-ocr`

## DeepSeek-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.

[See usage pricing →](https://flymy.ai/pricing/)

## 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.

## More vision and ocr models

Read images, video and scanned pages: describe them, pull out the text, answer questions about them.

### Gemini 3.8 Flash Vision

Gemini vision for photos, video and YouTube: OCR, comparisons and timestamped summaries.

Vision model / $0.75 / $3.75 per 1M tokens

Link: https://flymy.ai/mcp/models/gemini-3-8-flash-vlm/

### Qwen3-VL Instruct

Alibaba's Qwen3-VL for questions about photos, charts and scanned documents.

Vision model / $3.00 / hr

Link: https://flymy.ai/mcp/models/qwen3-vl-instruct-async/

## Go to the source

[DeepSeek-OCR in the playground →](https://app.flymy.ai/models/flymyai/deepseek-ocr), [Model endpoints in the docs →](https://docs.flymy.ai/api/models-endpoints), [Every model on FlyMy.AI →](https://flymy.ai/mcp/models/), [Every MCP in the catalog →](https://flymy.ai/mcp/#catalog), [Usage pricing →](https://flymy.ai/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.

---

For agents: the FlyMyAI operating guide (sign up, connect, run models, tools and agents) is https://flymy.ai/skill.md, and https://flymy.ai/llms.txt lists the other pages and the documentation.