MCP / Models / Vision and OCR
Gemini 3.8 Flash Vision MCP: read images and video
Google Gemini 3.8 Flash understands images, video and public YouTube links: it reads text, compares images, summarizes clips, returns text or JSON. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.
$ YOUR NEXT RUN
Any agentUse Gemini 3.8 Flash Vision 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/gemini-3-8-flash-vlm.md. Help me connect the FlyMy.AI MCP to this assistant, then run Gemini 3.8 Flash Vision (flymyai/gemini-3_8-flash-vlm) for this task: Read the text on this receipt photo with Gemini 3.8 Flash Vision and return it as JSON.
What Gemini 3.8 Flash Vision does
Give one media source: media_url (an image or video link, a YouTube link or a list of image URLs), an image upload or a video upload. Ask for a description, OCR, structured fields with response_format json and response_schema, or key moments with timestamps; start_offset, end_offset and fps narrow a video. max_output_tokens runs from 256 to 65,536.
Gemini 3.8 Flash Vision inputs
Every input of flymyai/gemini-3_8-flash-vlm as its live schema lists them. Returns analysis (string), kind (string), source (string), usage (string), finish_reason (string), reason (string).
| Input | Type, values and default |
|---|---|
# media_url | string optional Or a public URL: an image, a video, a YouTube link, or a JSON list of image URLs |
# prompt | string required What to answer about the media |
# image | file optional Allowed: image file, as a URL or upload Upload a photo, screenshot or scan |
# video | file optional Allowed: video file, as a URL or upload Upload a video clip |
# kind | string optional Allowed: auto, image, video Default: auto Only for media_url: set video for an extension-less video link |
# response_format | string optional Allowed: text, json Default: text json asks for a JSON body; describe its shape in the prompt |
# max_output_tokens | integer optional Allowed: 256 to 65536 Default: 8192 Answer ceiling; it also bounds the balance reservation |
# system_instruction | string optional Persona or output contract for the model |
# response_schema | string optional JSON Schema the answer must follow (JSON text or object); implies response_format json |
# thinking_level | string optional Allowed: high, medium, low Reasoning before the answer, billed as output; low suits labeling and extraction. Empty keeps the model default |
# temperature | number optional Allowed: 0 to 2 Sampling temperature |
# seed | integer optional Allowed: 0 to 2147483647 Sampling seed for more repeatable answers |
# fps | number optional Allowed: 0.1 to 24 Video only: frames read per second (Gemini default 1) |
# start_offset | number optional Allowed: from 0 Video only: second to start reading from |
# end_offset | number optional Allowed: from 0 Video only: second to stop reading at |
# media_resolution | string optional Allowed: high, medium, low How finely images and video frames are read: low spends fewer input tokens on an image, high costs a video about 3x. Empty keeps the model default |
Ask your agent
Requests to paste as they are, once the FlyMy.AI MCP is connected.
flymyai/gemini-3_8-flash-vlmflymyai/gemini-3_8-flash-vlmflymyai/gemini-3_8-flash-vlmGemini 3.8 Flash Vision price
$0.75 per 1M input tokens, $3.75 per 1M output tokens, cached input $0.075 per 1M. Cached input is $0.075 per 1M tokens. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.
Call Gemini 3.8 Flash Vision 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/gemini-3_8-flash-vlm",
"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/gemini-3_8-flash-vlm/predict/async/result/?request_id=<prediction_id>.
curl -X POST https://api.flymy.ai/api/v1/flymyai/gemini-3_8-flash-vlm/predict/async/ \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-F 'prompt=Describe this picture in two sentences.'Questions about Gemini 3.8 Flash Vision
Do I need a Google API key for Gemini 3.8 Flash Vision?
No. Gemini 3.8 Flash Vision runs on FlyMy.AI's account, so you need no Google key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.
How much does Gemini 3.8 Flash Vision cost?
$0.75 per 1M input tokens, $3.75 per 1M output tokens, cached input $0.075 per 1M. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-09.
How do I use Gemini 3.8 Flash Vision 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 Gemini 3.8 Flash Vision and return it as JSON." Your agent reads the inputs with get_model_schema and runs flymyai/gemini-3_8-flash-vlm with run_model.
What does Gemini 3.8 Flash Vision need as input?
Gemini 3.8 Flash Vision requires prompt; it also takes 15 optional inputs, each listed on this page with its allowed values and default.
Can I call Gemini 3.8 Flash Vision from my own code?
Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/gemini-3_8-flash-vlm/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.
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.