Together AI | Respan Docs

The Together AI SDK is the official Python client for Together’s inference platform, providing access to open-source models like Llama, Mistral, and more. Respan gives you full observability over every Together AI call, streamed response, and tool invocation — and gateway routing through the OpenAI-compatible Respan endpoint.

Set up Respan

Create an account at platform.respan.ai and grab an API key. For gateway, also add credits or a provider key.

Run npx @respan/cli setup to set up with your coding agent.

Example projects

Python examples

Tracing

Gateway

Setup

Install packages

$ pip install respan-ai opentelemetry-instrumentation-together together

Set environment variables

$ export TOGETHER_API_KEY="YOUR_TOGETHER_API_KEY"
$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

TOGETHER_API_KEY is used for Together requests. RESPAN_API_KEY is used to export traces to Respan.

Initialize and run

1 from together import Together
2 from respan import Respan
3 from opentelemetry.instrumentation.together import TogetherAiInstrumentor
4 
5 respan = Respan(instrumentations=[TogetherAiInstrumentor()])
6 
7 client = Together()
8 
9 response = client.chat.completions.create(
10     model="meta-llama/Llama-3-70b-chat-hf",
11     messages=[{"role": "user", "content": "Say hello in three languages."}],
12 )
13 print(response.choices[0].message.content)
14 respan.flush()

View your trace

Open the Traces page to see your auto-instrumented LLM spans.

Configuration

Parameter	Type	Default	Description
`api_key`	`str \| None`	`None`	Falls back to `RESPAN_API_KEY` env var.
`base_url`	`str \| None`	`None`	Falls back to `RESPAN_BASE_URL` env var.
`instrumentations`	`list`	`[]`	Plugin instrumentations to activate (e.g. `TogetherAiInstrumentor()`).
`customer_identifier`	`str \| None`	`None`	Default customer identifier for all spans.
`metadata`	`dict \| None`	`None`	Default metadata attached to all spans.
`environment`	`str \| None`	`None`	Environment tag (e.g. `"production"`).

Attributes

In Respan()

Set defaults at initialization — these apply to all spans.

1 from respan import Respan
2 from opentelemetry.instrumentation.together import TogetherAiInstrumentor
3 
4 respan = Respan(
5     instrumentations=[TogetherAiInstrumentor()],
6     customer_identifier="user_123",
7     metadata={"service": "chat-api", "version": "1.0.0"},
8 )

With propagate_attributes

Override per-request using a context scope.

1 from together import Together
2 from respan import Respan, propagate_attributes
3 from opentelemetry.instrumentation.together import TogetherAiInstrumentor
4 
5 respan = Respan(instrumentations=[TogetherAiInstrumentor()])
6 client = Together()
7 
8 def handle_request(user_id: str, question: str):
9     with propagate_attributes(
10         customer_identifier=user_id,
11         thread_identifier="conv_abc_123",
12         metadata={"plan": "pro"},
13     ):
14         response = client.chat.completions.create(
15             model="meta-llama/Llama-3-70b-chat-hf",
16             messages=[{"role": "user", "content": question}],
17         )
18         print(response.choices[0].message.content)

Attribute	Type	Description
`customer_identifier`	`str`	Identifies the end user in Respan analytics.
`thread_identifier`	`str`	Groups related messages into a conversation.
`metadata`	`dict`	Custom key-value pairs. Merged with default metadata.

Decorators (optional)

Decorators are not required. All Together AI calls are auto-traced. Use @workflow and @task to add structure when you want to group related calls into a named workflow with nested tasks.

1 from together import Together
2 from respan import Respan, workflow, task
3 from opentelemetry.instrumentation.together import TogetherAiInstrumentor
4 
5 respan = Respan(instrumentations=[TogetherAiInstrumentor()])
6 client = Together()
7 
8 @task(name="generate_outline")
9 def outline(topic: str) -> str:
10     response = client.chat.completions.create(
11         model="meta-llama/Llama-3-70b-chat-hf",
12         messages=[{"role": "user", "content": f"Create a brief outline about: {topic}"}],
13     )
14     return response.choices[0].message.content
15 
16 @workflow(name="content_pipeline")
17 def pipeline(topic: str):
18     print(outline(topic))
19 
20 pipeline("Benefits of API gateways")
21 respan.flush()