Vision Language Model

Understand images and text with Jina VLM.

APIPricing

Vision Language Model API

Explore the API. Make a real request. Use the code in your application.

API Key & UsageMore

Stream response

stream

Receive reasoning and answers as they are generated.

Maximum output tokens

max_tokens

Limit the length of the answer.

RequestPOST
curl 'https://chatsax.com/v1/chat/completions' \
  -X 'POST' \
  -H 'Content-Type: application/json' \
  -H "Authorization: Bearer $CHATSAX_API_KEY" \
  --data-binary '{
  "model": "jina-vlm",
  "messages": [
    {
      "role": "user",
      "content": "What are the practical differences between dense retrieval and reranking? Cite your sources."
    }
  ],
  "stream": true,
  "max_tokens": 1000
}'
Your response will appear here.
API keyNot connected

Give your agents better input.

Read a webpage, preserve the useful structure, and pass clean content into your retrieval or reasoning workflow.

Rendered content

Choose a browser engine and wait for the elements your application needs.

Control the output

Select Markdown, text, HTML, screenshots, or structured JSON responses.

A usable interface

Keep selectors, cache behavior, and content budgets in a reproducible request.

From playground to production.

Use the same request contract in the browser, an HTTP client, or your agent tools. A Chatsax key keeps access and usage separate from the upstream provider account.

Usage & access

Know what your requests use.

Chatsax currently uses invitation-based access. Request limits are assigned to each key; provider usage is recorded when available. No public checkout or standard price plan is offered here.

Your limits

View the current key’s scopes, minute limit, and daily request limit in the dashboard.

Recorded usage

Inspect requests, response status, latency, and available token counts.

Provider costs

Different services count usage differently. A cancelled or long-running request may still consume upstream resources.

Frequently asked questions

Does Reader crawl an entire website?

One request reads one resource. Recursive crawling needs a separate queue and URL policy.

Can it handle dynamic pages?

Use the browser engine, wait selectors, or rendering timing options. Some websites may still restrict automated access.

Are private cookies stored by Chatsax?

Cookie options are forwarded to the reading provider. Avoid sending unnecessary credentials and check the privacy policy before reading private content.

Is Chatsax operated by Jina AI?

Chatsax is independently operated. Jina supplies the current underlying APIs; model names and source links identify that provider.