Skip to main content
Version: v1.6.8 🚧

List vision capable LLMs

Overview​

Users can list the names of vision-capable multi-modal large language models (LLMs) available in the environment that can natively process images as input.

Example​

from h2ogpte import H2OGPTE

client = H2OGPTE(
    address="https://h2ogpte.genai.h2o.ai",
    api_key='sk-XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX',
)

vision_capable_llm_names = client.get_vision_capable_llm_names()

for llm in vision_capable_llm_names:
    print(llm)
auto
Qwen/Qwen2-VL-72B-Instruct
mistralai/Pixtral-12B-2409
meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
Qwen/Qwen2-VL-7B-Instruct
gemini-1.5-pro-latest
gemini-1.5-flash-latest
claude-3-haiku-20240307
claude-3-sonnet-20240229
claude-3-5-sonnet-20240620
gpt-4o
gpt-4o-mini
Feedback