Skip to main content
Together AI provides fast inference for a wide range of open-source models. The Together and AsyncTogether chat completions clients can be instrumented using the openinference-instrumentation-together package, which traces calls as OpenInference LLM spans.
This integration requires together >= 2.0.0.

Install

Setup

Set the TOGETHER_API_KEY environment variable to authenticate calls made using the SDK.
Connect your application to Phoenix with the register function: auto_instrument=True picks up the installed openinference-instrumentation-together package automatically. To instrument explicitly instead, call TogetherInstrumentor().instrument(tracer_provider=tracer_provider).

Run Together AI

A simple chat completion that is now instrumented:

Streaming

When stream=True, the span stays open until the stream is fully consumed, then records the accumulated output, tool calls, and token counts from the chunks.

Tool calls

Tools passed on the request (llm.tools.*) and any tool calls returned on the response (message.tool_calls.*) are captured on the span.

Observe

Now that you have tracing setup, all invocations of Together AI chat completions (sync and async, streaming and non-streaming) will be streamed to your running Phoenix for observability and evaluation.

Resources