This page is for **Respan LLM Gateway** users.

Use Respan Gateway to call Groq models (`llama-3.3-70b-versatile`, `llama-3.1-8b-instant`, `mixtral-8x7b-32768`, and the rest) while keeping unified observability (logs, cost, latency, reliability) in Respan.

## Quick setup

### Get a Respan API key

[Sign up](https://platform.respan.ai/) and create a key on the [API keys page](https://platform.respan.ai/platform/api/api-keys).

### Add credits (recommended)

[Top up credits](https://platform.respan.ai/platform/api/billing) to pay through Respan. No Groq key required, Respan handles provider auth and billing.

Prefer to route through your own Groq account? See [Use your own Groq key](/content/docs/integrations/gateway/model-providers/groq#use-your-own-groq-key-byok/index.html).

## Send your first request

Pick the integration that matches your stack. The base URL is `https://api.respan.ai/api` and the only key needed is your `RESPAN_API_KEY`.

###### Groq SDK

###### OpenAI SDK

###### Respan API

Point the official Groq SDK at the Respan gateway by overriding `base_url`.

## More integrations

Groq models work with every Respan gateway integration:

- [OpenAI SDK](/content/docs/integrations/openai-sdk/index.html)
- [OpenAI Agents SDK](/content/docs/integrations/openai-agents-sdk/index.html)
- [LangChain](/content/docs/integrations/langchain/index.html)
- [LlamaIndex](/content/docs/integrations/llama-index/index.html)
- [Pydantic AI](/content/docs/integrations/pydantic-ai/index.html)
- [Respan native (OTel)](/content/docs/documentation/features/gateway/gateway-quickstart/index.html)

## Switch models

Change the `model` parameter to call any supported model through the same client. Use the `groq/` prefix to disambiguate when routing across providers. Browse the full list on the [Models page](https://platform.respan.ai/platform/models).

## Use your own Groq key (BYOK)

Credits are the default path. If you’d rather bill Groq directly, attach your own provider key.

### Open Providers

Go to the [Providers page](https://platform.respan.ai/platform/api/providers).

### Add Groq

Select **Groq** and paste your `groq.api_key`.

### Load balancing (Optional)

Add multiple credential sets and use **Load balancing weight** to distribute traffic across them.

### Override credentials per model (Optional)

Use [`credential_override`](/content/docs/documentation/admin/llm_provider_keys#per-model-credential-override/index.html) when one model on a request should use a different Groq key than the default.

## Log without proxying (Optional)

Already calling Groq directly? Send logs to Respan asynchronously to track cost, latency, and performance for those external calls.

See the [logging guide](/content/docs/documentation/features/tracing/spans/index.html) for the full setup.