Groq

Set up Respan

Sign up — Create an account at platform.respan.ai
Create an API key — Generate one on the API keys page
Add credits or a provider key — Add credits on the Credits page or connect your own provider key on the Integrations page

Use AI

Add the Docs MCP to your AI coding tool to get help building with Respan. No API key needed.

{
  "mcpServers": {
    "respan-docs": {
      "url": "https://docs.respan.ai/mcp"
    }
  }
}

What is Groq?

The Groq SDK is the official Python client for Groq’s ultra-fast LPU inference engine, supporting chat completions and streaming with models like Llama and Mixtral. Respan can auto-instrument all Groq calls for tracing, route them through the Respan gateway, or both.

Setup

Install packages

Tracing
Gateway
Both

OpenInference (Recommended)
Traceloop

pip install respan-ai openinference-instrumentation-groq groq python-dotenv

pip install respan-ai opentelemetry-instrumentation-groq groq python-dotenv

pip install openai python-dotenv

OpenInference (Recommended)
Traceloop

pip install respan-ai openinference-instrumentation-groq groq openai python-dotenv

pip install respan-ai opentelemetry-instrumentation-groq groq openai python-dotenv

Set environment variables

Tracing
Gateway
Both

export GROQ_API_KEY="YOUR_GROQ_API_KEY"
export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

No GROQ_API_KEY needed — the Respan gateway handles provider authentication.

export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

No GROQ_API_KEY needed — the Respan gateway handles provider authentication.

Initialize and run

Tracing
Gateway
Both

OpenInference (Recommended)
Traceloop

import os
from dotenv import load_dotenv

load_dotenv()

from groq import Groq
from respan import Respan
from openinference.instrumentation.groq import GroqInstrumentor

# Initialize Respan with Groq instrumentation
respan = Respan(instrumentations=[GroqInstrumentor()])

# Calls go directly to Groq, auto-traced by Respan
client = Groq()

response = client.chat.completions.create(
    model="llama-3.1-70b-versatile",
    messages=[{"role": "user", "content": "Say hello in three languages."}],
)
print(response.choices[0].message.content)
respan.flush()

import os
from dotenv import load_dotenv

load_dotenv()

from groq import Groq
from respan import Respan

# Auto-discover and activate all installed instrumentors
respan = Respan(is_auto_instrument=True)

# Calls go directly to Groq, auto-traced by Respan
client = Groq()

response = client.chat.completions.create(
    model="llama-3.1-70b-versatile",
    messages=[{"role": "user", "content": "Say hello in three languages."}],
)
print(response.choices[0].message.content)
respan.flush()

import os
from dotenv import load_dotenv

load_dotenv()

from openai import OpenAI

# Route all LLM calls through the Respan gateway (OpenAI SDK format)
client = OpenAI(
    api_key=os.getenv("RESPAN_API_KEY"),
    base_url=os.getenv("RESPAN_BASE_URL", "https://api.respan.ai/api"),
)

response = client.chat.completions.create(
    model="llama-3.1-70b-versatile",
    messages=[{"role": "user", "content": "Say hello in three languages."}],
)
print(response.choices[0].message.content)

OpenInference (Recommended)
Traceloop

import os
from dotenv import load_dotenv

load_dotenv()

from openai import OpenAI
from respan import Respan
from openinference.instrumentation.groq import GroqInstrumentor

# Initialize Respan with Groq instrumentation
respan = Respan(instrumentations=[GroqInstrumentor()])

# Route all LLM calls through the Respan gateway
client = OpenAI(
    api_key=os.getenv("RESPAN_API_KEY"),
    base_url=os.getenv("RESPAN_BASE_URL", "https://api.respan.ai/api"),
)

response = client.chat.completions.create(
    model="llama-3.1-70b-versatile",
    messages=[{"role": "user", "content": "Say hello in three languages."}],
)
print(response.choices[0].message.content)
respan.flush()

import os
from dotenv import load_dotenv

load_dotenv()

from openai import OpenAI
from respan import Respan

# Auto-discover and activate all installed instrumentors
respan = Respan(is_auto_instrument=True)

# Route all LLM calls through the Respan gateway
client = OpenAI(
    api_key=os.getenv("RESPAN_API_KEY"),
    base_url=os.getenv("RESPAN_BASE_URL", "https://api.respan.ai/api"),
)

response = client.chat.completions.create(
    model="llama-3.1-70b-versatile",
    messages=[{"role": "user", "content": "Say hello in three languages."}],
)
print(response.choices[0].message.content)
respan.flush()

View your trace

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

This step applies to Tracing and Both setups. The Gateway-only setup does not produce traces.

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. `GroqInstrumentor()`).
`is_auto_instrument`	`bool \| None`	`False`	Auto-discover and activate all installed instrumentors via OpenTelemetry entry points.
`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

Attach customer identifiers, thread IDs, and metadata to spans.

In Respan()

Set defaults at initialization — these apply to all spans.

from respan import Respan
from openinference.instrumentation.groq import GroqInstrumentor

respan = Respan(
    instrumentations=[GroqInstrumentor()],
    customer_identifier="user_123",
    metadata={"service": "chat-api", "version": "1.0.0"},
)

With propagate_attributes

Override per-request using a context manager.

from respan import Respan, workflow, propagate_attributes
from openinference.instrumentation.groq import GroqInstrumentor
from groq import Groq

respan = Respan(
    instrumentations=[GroqInstrumentor()],
    metadata={"service": "chat-api", "version": "1.0.0"},
)
client = Groq()

@workflow(name="handle_request")
def handle_request(user_id: str, question: str):
    with propagate_attributes(
        customer_identifier=user_id,
        thread_identifier="conv_001",
        metadata={"plan": "pro"},  # merged with default metadata
    ):
        response = client.chat.completions.create(
            model="llama-3.1-70b-versatile",
            messages=[{"role": "user", "content": question}],
        )
        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

Use @workflow and @task to create structured trace hierarchies.

from respan import Respan, workflow, task
from openinference.instrumentation.groq import GroqInstrumentor
from groq import Groq

respan = Respan(instrumentations=[GroqInstrumentor()])
client = Groq()

@task(name="generate_outline")
def outline(topic: str) -> str:
    response = client.chat.completions.create(
        model="llama-3.1-70b-versatile",
        messages=[
            {"role": "user", "content": f"Create a brief outline about: {topic}"},
        ],
    )
    return response.choices[0].message.content

@workflow(name="content_pipeline")
def pipeline(topic: str):
    plan = outline(topic)
    response = client.chat.completions.create(
        model="llama-3.1-70b-versatile",
        messages=[
            {"role": "user", "content": f"Write content from this outline: {plan}"},
        ],
    )
    print(response.choices[0].message.content)

pipeline("Benefits of API gateways")
respan.flush()

Examples

Basic

response = client.chat.completions.create(
    model="llama-3.1-70b-versatile",
    messages=[{"role": "user", "content": "Say hello in three languages."}],
)
print(response.choices[0].message.content)

Streaming

stream = client.chat.completions.create(
    model="llama-3.1-70b-versatile",
    messages=[{"role": "user", "content": "Write a haiku about Python."}],
    stream=True,
)
for chunk in stream:
    content = chunk.choices[0].delta.content
    if content:
        print(content, end="", flush=True)

Gateway features

The features below require the Gateway or Both setup from Step 3.

Switch models

Change the model parameter to use 250+ models from different providers through the same gateway.

# Groq (Llama)
response = client.chat.completions.create(model="llama-3.1-70b-versatile", messages=messages)

# OpenAI
response = client.chat.completions.create(model="gpt-4.1-nano", messages=messages)

# Anthropic
response = client.chat.completions.create(model="claude-sonnet-4-5-20250929", messages=messages)

See the full model list.

Respan parameters

Pass additional Respan parameters via extra_body for gateway features.

response = client.chat.completions.create(
    model="llama-3.1-70b-versatile",
    messages=[{"role": "user", "content": "Hello"}],
    extra_body={
        "customer_identifier": "user_123",
        "fallback_models": ["gpt-4.1-nano"],
        "metadata": {"session_id": "abc123"},
        "thread_identifier": "conversation_456",
    },
)

See Respan parameters for the full list.

Overview

Agent Frameworks

LLM SDKs

Coding Agents

Vector DBs

Others

Model Providers

What is Groq?

Setup

Configuration

Attributes

In Respan()

With propagate_attributes

Decorators

Examples

Basic

Streaming

Gateway features

Switch models

Respan parameters

Overview

Agent Frameworks

LLM SDKs

Coding Agents

Vector DBs

Others

Model Providers

​What is Groq?

​Setup

​Configuration

​Attributes

​In Respan()

​With propagate_attributes

​Decorators

​Examples

​Basic

​Streaming

​Gateway features

​Switch models

​Respan parameters

What is Groq?

Setup

Configuration

Attributes

In Respan()

With propagate_attributes

Decorators

Examples

Basic

Streaming

Gateway features

Switch models

Respan parameters