Image Captioner

AI & Media Processing

Operated by Sourcelane✓ verified

Generates natural-language image captions using the Molmo 2 vision-language model (trained on 712,000+ human-described images). Produces captions at three granularity levels (brief one-liner, balanced description, detailed paragraph) and accepts an optional focus hint to direct attention to specific aspects (text, background, faces, objects). Supports bulk processing of image batches (up to 50 images per run) and returns one caption per image alongside the image source reference. Captions are crafted for use in SEO alt text, accessibility descriptions, content tagging, results annotation, and automated content review; typical per-image processing latency is on the order of seconds.

Verified Sep 28, 12:10 AM

$0.012

per result

Up to 83 per call. Only pay for results returned; failed calls are refunded.

What people use it for

E-commerce SEO: generate alt text for product images at scale
Accessibility compliance: produce descriptive alt text for websites and apps
Content moderation: pre-caption user-uploaded images for review workflows
results labeling: annotate image results for machine learning training
Digital asset management: auto-tag and describe large media libraries
Social media monitoring: caption scraped images to enable content search and indexing

Trust & reliability

7d uptime trend

Window	Uptime	Success rate	p50	p95
24h	—	—	—	—
7d	—	—	—	—
30d	—	—	—	—

Calling contract

Call it through Sourcelane's gateway or MCP server. We run the connector, apply your agent's spend guardrails, and bill only the results returned.

Call it via Sourcelane

curl -X POST https://cool-puffin-608.convex.site/v1/call \
  -H "Authorization: Bearer sl_live_your_agent_key" \
  -H "Content-Type: application/json" \
  -d '{"listing":"image-captioner","params":{"images":["https://i.imgur.com/TSem3Jf.jpeg","https://i.imgur.com/or3U2Xx.jpeg"]},"maxResults":10}'

Request params

Field	Type	Required	Description
`images`	array	optional	Images to caption. Each entry must be a publicly accessible http/https URL or a base64 data URI (data:image/jpeg;base64,...).
`imageFiles`	array	optional	Upload image files directly. Combined with any URLs provided above.
`detailLevel`	string	optional	How much detail to include in the caption. High produces the most descriptive output.
`focus`	string	optional	Optionally direct the model's attention to a specific aspect of the image - e.g. 'describe only the text visible' or 'focus on the background environment'.

Each result contains

Field	Type	Description
`inputImageUrl`	string	Input Image Url
`caption`	string	Caption
`detailLevel`	string	Detail Level
`status`	string	Status
`error`	null	—

Use Image Captioner from Claude, ChatGPT or Cursor

Pick your tool and connect in under a minute. Then just ask — for example: “Transcribe this video and give me timestamps for every product mention: <url>”

Connect Claude

Web, desktop and mobile. Paste one URL.

1Copy your personal connector URL
2In Claude open Settings → Connectors → Add custom connector
3Paste the URL and click Add — done

Manual setup (config files, REST, Python) +

Claude Code

Adds the Sourcelane MCP server with your key as a header.

terminal

claude mcp add --transport http sourcelane https://cool-puffin-608.convex.site/mcp \
  --header "Authorization: Bearer sl_live_your_agent_key"

Claude Desktop (config file)

Alternative to the connector URL: add to claude_desktop_config.json, then restart Claude.

claude_desktop_config.json

{
  "mcpServers": {
    "sourcelane": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://cool-puffin-608.convex.site/mcp",
        "--header",
        "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer sl_live_your_agent_key"
      }
    }
  }
}

Cursor & Windsurf

Add to ~/.cursor/mcp.json (or Windsurf's mcp_config.json).

mcp.json

{
  "mcpServers": {
    "sourcelane": {
      "url": "https://cool-puffin-608.convex.site/mcp",
      "headers": {
        "Authorization": "Bearer sl_live_your_agent_key"
      }
    }
  }
}

VS Code

Save as .vscode/mcp.json. VS Code prompts for your key once.

.vscode/mcp.json

{
  "servers": {
    "sourcelane": {
      "type": "http",
      "url": "https://cool-puffin-608.convex.site/mcp",
      "headers": {
        "Authorization": "Bearer ${input:sourcelane-key}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "sourcelane-key",
      "description": "Sourcelane agent key",
      "password": true
    }
  ]
}

ChatGPT Custom GPT (Actions)

Create a GPT → Actions → Import from URL, then Authentication: API Key, Bearer.

OpenAPI schema URL

https://sourcelane-amber.vercel.app/openapi.json

REST

One POST. Pass maxResults to cap cost.

curl

curl -X POST https://cool-puffin-608.convex.site/v1/call \
  -H "Authorization: Bearer sl_live_your_agent_key" \
  -H "Content-Type: application/json" \
  -d '{"listing":"image-captioner","params":{"images":["https://i.imgur.com/TSem3Jf.jpeg","https://i.imgur.com/or3U2Xx.jpeg"]},"maxResults":10}'

Python, LangChain, CrewAI, OpenAI Agents SDK…

Wrap the REST call as a tool, or point an MCP client at the endpoint.

python

import requests

res = requests.post(
    "https://cool-puffin-608.convex.site/v1/call",
    headers={"Authorization": "Bearer sl_live_your_agent_key"},
    json={
        "listing": "image-captioner",
        "params": {"images":["https://i.imgur.com/TSem3Jf.jpeg","https://i.imgur.com/or3U2Xx.jpeg"]},
        "maxResults": 10,
    },
    timeout=300,
)
body = res.json()
print(body["receipt"]["chargedMicros"], "micro-USD for", body["receipt"]["results"], "results")
print(body["data"])

Reviews

—

0 reviews

Leave a review

Loading reviews…