SDK v2 migration (Python)

​

Breaking changes

# v1 (positional arguments worked)
response = client.chat.completions.create("Qwen/Qwen3.5-9B", messages)

# v2 (keyword arguments required)
response = client.chat.completions.create(
    model="Qwen/Qwen3.5-9B",
    messages=messages,
    reasoning={"enabled": False},
)

response = client.chat.completions.create(
    model="Qwen/Qwen3.5-9B",
    messages=messages,
    reasoning={"enabled": False},
    extra_body={"custom_param": "value"},
)

​

Renamed methods

​

Changed response and input shapes

• List responses wrap results in .data: client.fine_tuning.list_checkpoints() and similar list calls return a response object, so iterate over response.data instead of the response itself.
• Downloads return content instead of writing to disk: files.content() and fine_tuning.content() return binary data. Write it to a file yourself, for example with response.iter_bytes() inside a with open(path, "wb") block.
• Audio uploads take file objects: audio.transcriptions.create() and audio.translations.create() require an open file object (with open("audio.mp3", "rb") as f:), not a path string.
• Voice listing uses attribute access: Read each listed voice’s fields as attributes, for example voice.name instead of voice["name"].
• Checkpoint fields are renamed: type is now checkpoint_type, and timestamp is now created_at. The name field is gone, so construct it from the job ID and step.
• Batch creation returns a wrapper: batches.create() returns a response object with the job at response.job.
• Evaluations use typed parameter objects: evals.create() takes a parameters object (for example, ParametersEvaluationClassifyParameters from together.types.eval_create_params) instead of top-level keyword arguments. retrieve() and status() take the workflow ID as a positional argument.

​

Exception changes

​

Getting help

• Browse the SDK source in the together-py repo.
• The API reference shows v2 code examples for every endpoint.
• Report issues on Discord or contact support.