Instruct-tuned open model by Google with excellent ELO/size tradeoff and vision capabilities
from openai import OpenAI import os model_url = "" # Copy in from API pane in Baseten model dashboard client = OpenAI( api_key=os.environ['BASETEN_API_KEY'], base_url=model_url ) # Chat completion response_chat = client.chat.completions.create( model="", messages=[{ "role": "user", "content": [ {"type": "text", "text": "What's in this image?"}, { "type": "image_url", "image_url": { "url": "https://picsum.photos/id/237/200/300", }, }, ], }], temperature=0.3, max_tokens=512, ) print(response_chat)
{ "id": "143", "choices": [ { "finish_reason": "stop", "index": 0, "logprobs": null, "message": { "content": "[Model output here]", "role": "assistant", "audio": null, "function_call": null, "tool_calls": null } } ], "created": 1741224586, "model": "", "object": "chat.completion", "service_tier": null, "system_fingerprint": null, "usage": { "completion_tokens": 145, "prompt_tokens": 38, "total_tokens": 183, "completion_tokens_details": null, "prompt_tokens_details": null } }
Was this page helpful?