Together AI Python API Docs | dltHub

Together AI is a platform and REST API to run, fine‑tune, and serve open‑source and specialized AI models (serverless and dedicated) for inference and training. The REST API base URL is https://api.together.xyz/v1 and all requests require a Bearer token for authentication.

dlt is an open-source Python library that handles authentication, pagination, and schema evolution automatically. dlthub provides AI context files that enable code assistants to generate production-ready pipelines. Install with uv pip install "dlt[workspace]" and start loading Together AI data in under 10 minutes.

---

What data can I load from Together AI?

Here are some of the endpoints you can load from Together AI:

---

How do I authenticate with the Together AI API?

API uses a single API key presented as a Bearer token in the Authorization header. Include header: Authorization: Bearer <YOUR_API_KEY> and Content-Type: application/json for JSON requests.

1. Get your credentials

1. Sign in to your Together AI account.
2. Open the API keys/settings page at https://api.together.ai/settings/api-keys (or the API Keys section in the dashboard).
3. Create a new API key and copy the value.
4. Store the key securely (do not commit to source control) and use it in the Authorization header.

2. Add them to .dlt/secrets.toml

Copy
[sources.together_ai_source]
api_key = "your_together_api_key_here"

dlt reads this automatically at runtime — never hardcode tokens in your pipeline script. For production environments, see setting up credentials with dlt for environment variable and vault-based options.

---

How do I set up and run the pipeline?

Set up a virtual environment and install dlt:

Copy
uv venv && source .venv/bin/activate
uv pip install "dlt[workspace]"

1. Install the dlt AI Workbench:

Copy
dlt ai init --agent <your-agent> # <agent>: claude | cursor | codex

This installs project rules, a secrets management skill, appropriate ignore files, and configures the dlt MCP server for your agent. Learn more →

2. Install the rest-api-pipeline toolkit:

Copy
dlt ai toolkit rest-api-pipeline install

This loads the skills and context about dlt the agent uses to build the pipeline iteratively, efficiently, and safely. The agent uses MCP tools to inspect credentials — it never needs to read your secrets.toml directly. Learn more →

3. Start LLM-assisted coding:

Use /find-source to load data from the Together AI API into DuckDB.

The rest-api-pipeline toolkit takes over from here — it reads relevant API documentation, presents you with options for which endpoints to load, and follows a structured workflow to scaffold, debug, and validate the pipeline step by step.

4. Run the pipeline:

Copy
python together_ai_pipeline.py

If everything is configured correctly, you'll see output like this:

Copy
Pipeline together_ai_pipeline load step completed in 0.26 seconds
1 load package(s) were loaded to destination duckdb and into dataset together_ai_data
The duckdb destination used duckdb:/together_ai.duckdb location to store data
Load package 1749667187.541553 is LOADED and contains no failed jobs

Inspect your pipeline and data:

Copy
dlt pipeline together_ai_pipeline show

This opens the Pipeline Dashboard where you can verify pipeline state, load metrics, schema (tables, columns, types), and query the loaded data directly.

---

Python pipeline example

This example loads endpoints and chat_completions from the Together AI API into DuckDB. It mirrors the endpoint and data selector configuration from the table above:

Copy
import dlt
from dlt.sources.rest_api import RESTAPIConfig, rest_api_resources

@dlt.source
def together_ai_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://api.together.xyz/v1",
            "auth": {
                "type": "bearer",
                "token": api_key,
            },
        },
        "resources": [
            {"name": "endpoints", "endpoint": {"path": "endpoints", "data_selector": "data"}},
            {"name": "models", "endpoint": {"path": "serverless-models", "data_selector": "data"}}
        ],
    }
    yield from rest_api_resources(config)


def get_data() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="together_ai_pipeline",
        destination="duckdb",
        dataset_name="together_ai_data",
    )
    load_info = pipeline.run(together_ai_source())
    print(load_info)

To add more endpoints, append entries from the resource table to the "resources" list using the same name, path, and data_selector pattern.

---

How do I query the loaded data?

Once the pipeline runs, dlt creates one table per resource. You can query with Python or SQL.

Python (pandas DataFrame):

Copy
import dlt

data = dlt.pipeline("together_ai_pipeline").dataset()
sessions_df = data.endpoints.df()
print(sessions_df.head())

SQL (DuckDB example):

Copy
SELECT * FROM together_ai_data.endpoints LIMIT 10;

In a marimo or Jupyter notebook:

Copy
import dlt

data = dlt.pipeline("together_ai_pipeline").dataset()
data.endpoints.df().head()

See how to explore your data in marimo Notebooks and how to query your data in Python with dataset.

---

What destinations can I load Together AI data to?

dlt supports loading into any of these destinations — only the destination parameter changes:

Change the destination in dlt.pipeline(destination="snowflake") and add credentials in .dlt/secrets.toml. See the full destinations list.

---

Troubleshooting

Authentication failures

If you receive 401 or 403 responses, verify your API key is valid and sent in the Authorization: Bearer <KEY> header. Check the API key in the dashboard and ensure it hasn't been revoked.

Rate limits and 429 errors

If you receive 429 Too Many Requests, back off and retry with exponential backoff. Inspect response headers for rate‑limit details if they are provided.

Server and 5xx errors

500/502/503 responses indicate transient server errors. Retry with exponential backoff; contact Together support if the problem persists.

Ensure that the API key is valid to avoid 401 Unauthorized errors. Also, verify endpoint paths and parameters to avoid 404 Not Found errors.

---

Next steps

Continue your data engineering journey with the other toolkits of the dltHub AI Workbench:

• data-exploration — Build custom notebooks, charts, and dashboards for deeper analysis with marimo notebooks.
• dlthub-runtime — Deploy, schedule, and monitor your pipeline in production.

Copy
dlt ai toolkit data-exploration install
dlt ai toolkit dlthub-runtime install

• How to deploy a pipeline
• How to explore your data in marimo Notebooks
• How to query your data in Python with dataset
• Join the dlt community on Slack