Skip to navigation
ModelsMore providers

Provider: Together AI

Call Together AI models through Respan Gateway with unified logs, cost, and latency.
This page is for Respan LLM Gateway users.

Use Respan Gateway to call Together AI models (together_ai/Qwen/Qwen3.8-Flash, together_ai/deepseek-ai/DeepSeek-V4.1-Flash, together_ai/zai-org/GLM-5.3, and more) while keeping unified observability (logs, cost, latency, reliability) in Respan.

Together AI requires bring your own key (BYOK). Provider usage cannot be paid with Respan credits.

Quick setup

1

Get a Respan API key

Sign up and create a key on the API keys page.

2

Add your Together AI credentials

Configure your Together AI credentials on the Providers page before using the examples below. See Use your own Together AI key.

Send your first request

After configuring your Together AI credentials in Respan, pick the integration that matches your stack. The base URL is https://api.respan.ai/api and your application authenticates with RESPAN_API_KEY.

The Together Python SDK accepts a base_url override. Point it at the Respan gateway to keep your existing Together code.

Python
from together import Together
client = Together(
    api_key="YOUR_RESPAN_API_KEY",
    base_url="https://api.respan.ai/api",
)
response = client.chat.completions.create(
    model="together_ai/Qwen/Qwen3.8-Flash",
    messages=[{"role": "user", "content": "Hello, Together!"}],
)
print(response.choices[0].message.content)

More integrations

Together AI models work with every Respan gateway integration:

Switch models

Change the model parameter to call any supported model through the same client. Use the together_ai/ prefix to disambiguate when routing across providers. Browse the full list on the Models page.

client.chat.completions.create(model="together_ai/Qwen/Qwen3.8-Flash", messages=messages)
client.chat.completions.create(model="together_ai/deepseek-ai/DeepSeek-V4.1-Flash", messages=messages)
client.chat.completions.create(model="together_ai/zai-org/GLM-5.3", messages=messages)
client.chat.completions.create(model="openai/gpt-6-sol", messages=messages)
client.chat.completions.create(model="anthropic/claude-opus-5-5", messages=messages)

Use your own Together AI key (BYOK)

Together AI credentials are required. Configure them in Respan or pass them with each request using one of the options below.

1

Open Providers

Go to the Providers page.

2

Add Together AI

Select Together AI and paste your togetherai.api_key. Grab one from the Together API keys page.

3

Load balancing (Optional)

Add multiple credential sets and use Load balancing weight to distribute traffic across them.

Override credentials per model (Optional)

Use credential_override when one model on a request should use a different Together AI key than the default.

{
  "customer_credentials": {
    "togetherai": { "api_key": "YOUR_TOGETHERAI_API_KEY" }
  },
  "credential_override": {
    "together_ai/Qwen/Qwen3.8-Flash": { "api_key": "ANOTHER_TOGETHERAI_API_KEY" }
  }
}

Log without proxying (Optional)

Already calling Together AI directly? Send logs to Respan asynchronously to track cost, latency, and performance for those external calls.

import requests
requests.post(
    "https://api.respan.ai/api/request-logs/create/",
    headers={
        "Authorization": "Bearer YOUR_RESPAN_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "together_ai/Qwen/Qwen3.8-Flash",
        "prompt_messages": [{"role": "user", "content": "Hello, how are you?"}],
        "completion_message": {"role": "assistant", "content": "Hello from Together AI through Respan."},
        "cost": 0.001,
        "generation_time": 1.2,
        "customer_params": {"customer_identifier": "user_123"},
    },
)

See the logging guide for the full setup.