Skip to main content
Groq offers a Chat Completions API at a documented compatibility endpoint. Prepare the candidate below and use Threetone’s dashboard probe to check the specific model and credentials.
Connection testing is available, but custom-model publication and execution are unavailable. A successful probe is not a provider compatibility guarantee or a production release.

​
Candidate settings

Use the base URL from Groq’s compatibility documentation. Keep /chat/completions out of Server URL. Groq documents differences in supported parameters; compatibility with a client library does not mean every request or model feature is interchangeable.

​
Check the connection

1

Choose one chat model

Verify its current availability and limits in your provider account. Keep the exact model ID with your test record so a later model replacement is reviewed deliberately.
2

Configure the secret reference

In the agent’s Custom LLM settings, enter the server URL and model ID, then select the API-key reference. Environment references use their production value during the probe. See custom models for the complete field workflow.
3

Inspect the streaming result

Select Test connection only with approval to make a real provider request. The probe uses streaming Chat Completions with usage reporting requested and requires a nonempty assistant text delta. A model that only returns another response shape will fail this check.
Separate authentication errors, model-access errors, rate limits, and unsupported parameters when diagnosing failures. Do not add speculative headers or switch API types to bypass a failed probe; review the accepted endpoint contract. Local edits are not a published version. If you need a durable candidate for review, save a complete server draft and read it back. Compare it with managed model options before planning a release.

​
Frequently asked questions

No SDK installation is part of this dashboard probe. You supply the endpoint, model identifier, and protected credential reference.
No. It checks the probe’s request and text stream. Tool behavior, conversation execution, speech, and end-to-end latency require separate supported runtime tests.