Image understanding · OCR · Docs

Vision (VLM / OCR)

Beta

Multimodal chat that accepts images, plus document OCR and table extraction.

Overview

Vision (VLM / OCR)

Use it for screenshot analysis, image Q&A, reading receipts and forms, and screen understanding for UI automation. For image understanding, send `image_url` content parts (https URL or data URL) to a multimodal (VL) chat model on `/v1/chat/completions`. For document text, send an image or PDF as base64 to `POST /v1/ocr` and get per-page text back (billed per page).

Endpoint: /v1/chat/completions
Example model: qwen2.5-vl-7b

API

API example

# 1) discover an online vision-capable (VL) chat model — Grid's set
#    changes constantly, don't hardcode an id in your code.
MODEL=$(curl -s https://api.openalchemy.io/v1/models \
  -H "Authorization: Bearer $OPENALCHEMY_API_KEY" \
  | jq -r '.data[] | select(.online and .endpoint_type=="chat" and (.id | test("vl|vision"; "i"))) | .id' \
  | head -1)

# 2) ask about an image (https URL or data: URL)
curl https://api.openalchemy.io/v1/chat/completions \
  -H "Authorization: Bearer $OPENALCHEMY_API_KEY" \
  -H "X-Project-Id: $YOUR_PROJECT_ID" \
  -H "Content-Type: application/json" \
  -d "{
    \"model\": \"$MODEL\",
    \"messages\": [
      {\"role\": \"user\", \"content\": [
        {\"type\": \"text\", \"text\": \"What is in this image?\"},
        {\"type\": \"image_url\", \"image_url\": {\"url\": \"https://example.com/receipt.jpg\"}}
      ]}
    ]
  }"

Status

Quota and pricing (per project)

Allotments and rate limits apply to the project that issued the API key. A second domain-scoped policy layer constrains which origins may invoke each modality.

Read the docs for this modality →

START TODAY

Ready to turn inference cost into something closer to alchemy?

Get started free See pricing