Skip to content

OpenAI · chat

gpt-4-vision-preview

openai/gpt-4-vision-preview

Input price
$10.0 / 1M tokens
Output price
$30.0 / 1M tokens
Context window
128K tokens
Lifecycle
deprecated

gpt-4-vision-preview for OpenAI-compatible gateway routing

gpt-4-vision-preview is a OpenAI chat model in the Ferro Labs live catalog with a 128K tokens context window, 4K tokens maximum output, and capabilities including Vision, Prompt Caching, and Streaming.

Token pricing is listed as $10.0 / 1M tokens for input tokens and $30.0 / 1M tokens for output tokens. Route calls through the Ferro Labs AI Gateway by sending model as openai/gpt-4-vision-preview to the OpenAI-compatible chat completions endpoint. The catalog marks this model as deprecated; plan a migration before routing new workloads.

OpenAI-compatible usage example

curl https://api.ferrolabs.ai/v1/chat/completions \
  -H "Authorization: Bearer $GATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "openai/gpt-4-vision-preview", "messages": [{"role": "user", "content": "Hello!"}]}'

Capabilities

  • Vision
  • Prompt Caching
  • Streaming

Modalities

Input

  • Text
  • Image

Output

  • Text

More from OpenAI

Catalog prices may change. Verify current provider terms before purchasing.