OpenRouter.ai
Base_URL: https://openrouter.ai/api/v1
------------------------------------------------------------------
GitHub Models https://github.com/marketplace/models/
Base_URL: https://models.github.ai/inference
Model: openai/gpt-4o-mini
------------------------------------------------------------------
Groq groq.com
Base_URL: https://api.groq.com/openai/v1
------------------------------------------------------------------
Nebius nebius.com
Base_URL: https://api.studio.nebius.com/v1/
------------------------------------------------------------------
Hugging Face huggingface.co
Base_URL: https://router.huggingface.co/v1
!!! В названии модели нужно указывать провайдера
Пример: meta-llama/Llama-3.1-8B-Instruct:nebius
------------------------------------------------------------------
Google Gemini aistudio.google.com
Base_URL: https://generativelanguage.googleapis.com/v1beta/openai
------------------------------------------------------------------
Mistral.ai
Base_URL: https://api.mistral.ai/v1
------------------------------------------------------------------
Cerebras.ai
Base_URL: https://api.cerebras.ai/v1
------------------------------------------------------------------
Sambanova.ai
Base_URL: в личном кабинете
------------------------------------------------------------------
Fireworks.AI
Base_URL: https://api.fireworks.ai/inference/v1
------------------------------------------------------------------
IO.NET
Base_URL: https://api.intelligence.io.solutions/api/v1

import os
from azure.ai.inference import ChatCompletionsClient
from azure.ai.inference.models import SystemMessage
from azure.ai.inference.models import UserMessage
from azure.core.credentials import AzureKeyCredential

client = ChatCompletionsClient(
    endpoint="https://models.github.ai/inference",
    credential=AzureKeyCredential(os.environ["GITHUB_TOKEN"]),
)
response = client.complete(
    messages=[
        SystemMessage(""""""),
        UserMessage("Can you explain the basics of machine learning?"),
    ],
    model="openai/gpt-4o",
    temperature=1,
    max_tokens=4096,
    top_p=1
)
print(response.choices[0].message.content)