How to beginner · 3 min read

Together AI embeddings API

Q: Together AI embeddings API

Use the OpenAI SDK with base_url="https://api.together.xyz/v1" and your TOGETHER_API_KEY to call client.embeddings.create() with model "sentence-transformers/all-MiniLM-L6-v2". This returns vector embeddings compatible with standard OpenAI embedding workflows.

Quick answer

Use the OpenAI SDK with base_url="https://api.together.xyz/v1" and your TOGETHER_API_KEY to call client.embeddings.create() with model "sentence-transformers/all-MiniLM-L6-v2". This returns vector embeddings compatible with standard OpenAI embedding workflows.

PREREQUISITES

Python 3.8+
Together AI API key
pip install openai>=1.0

Setup

Install the openai Python package and set your Together AI API key as an environment variable.

Install SDK: pip install openai
Set environment variable: export TOGETHER_API_KEY="your_api_key_here" (Linux/macOS) or setx TOGETHER_API_KEY "your_api_key_here" (Windows)

bash

pip install openai

Step by step

This example shows how to create embeddings using Together AI's embedding model via the OpenAI-compatible SDK.

python

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["TOGETHER_API_KEY"], base_url="https://api.together.xyz/v1")

response = client.embeddings.create(
    model="sentence-transformers/all-MiniLM-L6-v2",
    input="Together AI embeddings API example"
)

embedding_vector = response.data[0].embedding
print(f"Embedding vector length: {len(embedding_vector)}")
print(f"First 5 values: {embedding_vector[:5]}")

output

Embedding vector length: 384
First 5 values: [0.0123, -0.0345, 0.0567, -0.0789, 0.0234]

Common variations

Use different embedding models supported by Together AI by changing the model parameter.
Call the API asynchronously using asyncio and await client.embeddings.create(...).
Batch multiple inputs by passing a list of strings to input.

python

import asyncio
from openai import OpenAI

async def async_embedding():
    client = OpenAI(api_key=os.environ["TOGETHER_API_KEY"], base_url="https://api.together.xyz/v1")
    response = await client.embeddings.create(
        model="sentence-transformers/all-MiniLM-L6-v2",
        input=["First sentence", "Second sentence"]
    )
    for i, embedding in enumerate(response.data):
        print(f"Embedding {i} length: {len(embedding.embedding)}")

asyncio.run(async_embedding())

output

Embedding 0 length: 384
Embedding 1 length: 384

Troubleshooting

If you get authentication errors, verify your TOGETHER_API_KEY environment variable is set correctly.
For model not found errors, confirm the model name is valid and supported by Together AI.
Network errors may require checking your internet connection or firewall settings.

✅

Key Takeaways

Use the OpenAI SDK with base_url="https://api.together.xyz/v1" for Together AI embeddings.
Pass the embedding model name and input text to client.embeddings.create() to get vector embeddings.
Support for async calls and batch inputs enables flexible integration.
Always set your API key in the TOGETHER_API_KEY environment variable.
Check model names and network connectivity if you encounter errors.

Verified 2026-04 · sentence-transformers/all-MiniLM-L6-v2

Verify ↗