Llama cURL Integration - Helicone OSS LLM Observability

Warning

This integration method is maintained but no longer actively developed. For the best experience and latest features, use our new AI Gateway with unified API access to 100+ models.

Create an account + Generate an API Key

Log into Helicone or create an account. Once you have an account, you can generate an API key.

Modify the API base and add the `Helicone-Auth` header

curl -X POST https://llama.helicone.ai/v1/chat/completions \  -H "Content-Type: application/json" \  -H "Authorization: Bearer $LLAMA_API_KEY" \  -H "Helicone-Auth: Bearer $HELICONE_API_KEY" \  -d '{    "model": "Llama-4-Maverick-17B-128E-Instruct-FP8",    "messages": [      {        "role": "user",        "content": "Hello, how are you?"      }    ],    "max_completion_tokens": 1024,    "temperature": 0.7  }'

Verify your requests in Helicone

With the above setup, any calls to the Llama API will automatically be logged and monitored by Helicone. Review them in your Helicone dashboard.