Together AI Free API: $5 Credits, Llama, DeepSeek & FLUX Free

Provider fit matrix

Production readiness checklist

Python setup snapshot

Start with the smallest possible embeddings request, then move the key to your server-side secret manager before production.

from openai import OpenAI

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

# LLM 对话
response = client.chat.completions.create(
    model="meta-llama/Llama-3.3-70B-Instruct-Turbo",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

# FLUX 免费图片生成
import requests

response = requests.post(
    "https://api.together.xyz/v1/images/generations",
    headers={"Authorization": "Bearer together-your-api-key"},
    json={
        "model": "black-forest-labs/FLUX.1-schnell-Free",
        "prompt": "A cute cat wearing sunglasses",
        "n": 1,
        "size": "1024x1024"
    }
)
print(response.json())

cURL smoke test

Use this to verify endpoint, auth header, model name, response shape, and quota before adding SDK abstractions.

curl https://api.together.xyz/v1/embeddings \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Llama 3.3 70B Turbo",
    "input": "Hello from yangmao.ai"
  }'

Decision checklist

Related internal links

FAQ