ai.describe-image

Describe an image. POST { imageUrl, instruction? }. Returns { imageUrl, altText (5-15 word accessibility text), description (2-3 sentences), contentType (photograph|illustration|screenshot|diagram|document|mixed|other), text (verbatim OCR transcription, "" if none), mainObjects[], dominantColors[] (hex) }. Accepts JPEG, PNG, GIF, WebP. 1MB image size cap.

price
$0.0180 USDC per call
method
POST/api/ai/describe-image
payment
x402 v2 · EIP-3009 transferWithAuthorization · USDC on Base mainnet
auth
None. Sign the payment, retry with PAYMENT-SIGNATURE.
tier
Tier 2 — LLM/render upstream included

Parameters

NameTypeDescription
imageUrlrequiredstringHTTPS URL of a JPEG, PNG, GIF, or WebP image (≤1MB).
max 2048 chars · uri
instructionstringOptional caller-supplied focus hint, e.g. "describe the chart axes".
max 1000 chars

Code samples

cURLbash
# 1. Probe the endpoint with no auth — receive 402 with PaymentRequirements
curl -sS -X POST 'https://2s.io/api/ai/describe-image' \
  -H 'Content-Type: application/json' \
  -d '{"imageUrl":"https://example.com","instruction":"example"}'

# 2. Sign the EIP-3009 transferWithAuthorization for the advertised price +
#    payTo from the 402 envelope, then retry with PAYMENT-SIGNATURE:
curl -sS -X POST 'https://2s.io/api/ai/describe-image' \
  -H 'Content-Type: application/json' \
  -H 'PAYMENT-SIGNATURE: <base64-json-payload>' \
  -d '{"imageUrl":"https://example.com","instruction":"example"}'

# Or just use the canonical runner — it handles the whole loop:
#   EVM_PRIVATE_KEY=0x... node --env-file=.env.local \
#     --experimental-strip-types scripts/x402-pay.ts \
#     'https://2s.io/api/ai/describe-image'
TypeScript / Node — @2sio/sdktypescript
import { TwoS } from '@2sio/sdk'

const client = new TwoS({
  privateKey: process.env.EVM_PRIVATE_KEY as `0x${string}`,
})

const result = await client.ai.describeImage({
  "imageUrl": "https://example.com",
  "instruction": "example"
})

console.log('endpoint:', result.endpoint)
console.log('cost:', result.costUsd, 'USDC')
console.log('tx:', result.settlement?.txHash)
console.log('data:', result.data)
Python — 2siopython
import os
from twosio import TwoS

client = TwoS(private_key=os.environ["EVM_PRIVATE_KEY"])

result = client.ai.describe_image(imageUrl="https://example.com", instruction="example")

print("endpoint:", result.endpoint)
print("cost:", result.cost_usd, "USDC")
print("tx:", (result.settlement or {}).get("tx_hash"))
print("data:", result.data)
MCP — Claude Desktop / AgentKit / any MCP hostjson
// 1. Add @2sio/mcp to your MCP host config (Claude Desktop example below).
//    EVM_PRIVATE_KEY funds x402 payments per call.

// claude_desktop_config.json
{
  "mcpServers": {
    "2sio": {
      "command": "npx",
      "args": ["-y", "@2sio/mcp"],
      "env": { "EVM_PRIVATE_KEY": "0x..." }
    }
  }
}

// 2. Once the server is running, agents call this tool via standard MCP:

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "ai.describe-image",
    "arguments": {
      "imageUrl": "https://example.com",
      "instruction": "example"
    }
  }
}

Response

FieldTypeDescription
imageUrlstring
altTextstringShort accessibility text (~5-15 words).
descriptionstring2-3 sentence description.
contentTypestring
one of: photograph | illustration | screenshot | diagram | document | mixed | other
textstringVerbatim OCR transcription, "" if no text present.
mainObjectsarraySalient objects/subjects in the image.
dominantColorsarrayHex color codes (e.g. "#1a3b5f") of dominant colors.
Example response datajson
{
  "imageUrl": "example",
  "altText": "example",
  "description": "example",
  "contentType": "photograph",
  "text": "example",
  "mainObjects": [
    "example"
  ],
  "dominantColors": [
    "example"
  ]
}

Discovery

2s.io is x402-native. Every call is paid per-request from a USDC-funded EVM wallet on Base — no signup, no API keys, no monthly fees. Source code: github.com/2s-io/sdk.