from openai import OpenAI

# Just modify base_url and api_key
client = OpenAI(
    base_url="https://api.together.xyz/v1",
    api_key="your-together-api-key"
)

response = client.chat.completions.create(
    model="meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
    messages=[
        {"role": "user", "content": "Explain what RAG technology is"}
    ],
    max_tokens=1000
)
print(response.choices[0].message.content)

Together AI main models and prices (2025):




High quality model:


- Llama-3.1-70B-Instruct: $0.88/million tokens


- Qwen2.5-72B-Instruct: $1.2/million tokens


- DeepSeek-V3: $0.27/million tokens




Fast and lightweight model:


- Llama-3.2-3B-Instruct: $0.06/million tokens


- Llama-3.1-8B-Instruct: $0.18/million tokens




Compare OpenAI:


- GPT-4o: $2.5/million input tokens


- GPT-4o-mini: $0.15/million input tokens

import together

client = together.Together(api_key="your-key")

# Batch process multiple texts
texts = [
    "Please summarize:" + text
    for text in long_texts_list
]

# Concurrent calls
import asyncio
from together import AsyncTogether

async def process_batch(texts):
    async_client = AsyncTogether(api_key="your-key")
    tasks = [
        async_client.chat.completions.create(
            model="meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
            messages=[{"role": "user", "content": text}]
        )
        for text in texts
    ]
    return await asyncio.gather(*tasks)

results = asyncio.run(process_batch(texts))