GPT-4 Turbo (batch)

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.

ChatOpenAI128k tokens$5.4503 / $16.3509 · 1M

openai/gpt-4-turbo:batch

Context
128k tokens
Completion cap
4,096
Tools
Yes
JSON
Yes
Released
2024-04-09

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4-turbo:batch",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is GPT-4 Turbo (batch)?
The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023. GPT-4 Turbo (batch) runs on the Geek Hub API (OpenAI-compatible). Model id: openai/gpt-4-turbo:batch.
Is GPT-4 Turbo (batch) free?
No. Input is $5.4503 per 1M tokens and output is $16.3509 per 1M tokens on Geek Hub (markup included).
What is the context length of GPT-4 Turbo (batch)?
GPT-4 Turbo (batch) has a 128k tokens context window. It supports up to 4,096 completion tokens.
Does GPT-4 Turbo (batch) support tool calling and structured outputs?
GPT-4 Turbo (batch) accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was GPT-4 Turbo (batch) released?
GPT-4 Turbo (batch) was released on 2024-04-09.

More models from OpenAI