Vision

Models with image input take images as image_url content parts in a user message. Which models: the ones marked “vision” on the models page, for example zai-org/glm-5.3-flash, google/gemma-4-31b-it, moonshotai/kimi-k3 and deepseek/deepseek-v4.1-flash. Text-only models refuse or ignore images.

Image by URL

The URL must be publicly reachable: the provider downloads it.

curl

curl https://api.thetoken.dev/v1/chat/completions \
  -H "Authorization: Bearer $TOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org/glm-5.3-flash",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "Describe this image in one sentence."},
        {"type": "image_url", "image_url": {"url": "https://thetoken.dev/brand/og-image.png"}}
      ]
    }]
  }'

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.thetoken.dev/v1", api_key=os.environ["TOKEN_API_KEY"])

response = client.chat.completions.create(
    model="zai-org/glm-5.3-flash",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Describe this image in one sentence."},
            {"type": "image_url", "image_url": {"url": "https://thetoken.dev/brand/og-image.png"}},
        ],
    }],
)
print(response.choices[0].message.content)

TypeScript

import OpenAI from 'openai'

const client = new OpenAI({ baseURL: 'https://api.thetoken.dev/v1', apiKey: process.env.TOKEN_API_KEY })

const response = await client.chat.completions.create({
  model: 'zai-org/glm-5.3-flash',
  messages: [
    {
      role: 'user',
      content: [
        { type: 'text', text: 'Describe this image in one sentence.' },
        { type: 'image_url', image_url: { url: 'https://thetoken.dev/brand/og-image.png' } },
      ],
    },
  ],
})
console.log(response.choices[0].message.content)

Image from a file

Send local images as a base64 data: URL:

import base64
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.thetoken.dev/v1", api_key=os.environ["TOKEN_API_KEY"])

with open("receipt.jpg", "rb") as f:
    data_url = "data:image/jpeg;base64," + base64.b64encode(f.read()).decode()

response = client.chat.completions.create(
    model="google/gemma-4-31b-it",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "What is the total on this receipt?"},
            {"type": "image_url", "image_url": {"url": data_url}},
        ],
    }],
)
print(response.choices[0].message.content)

Good to know

• Images count as input tokens, billed at the model’s input price; the usage of the response shows the total.
• On /v1/messages, send images as Anthropic image blocks ({"type": "image", "source": {"type": "base64", "media_type": "image/png", "data": "..."}}).