GroqCloud for your agents.
Connect GroqCloud once and every agent you run inside Even (Claude Code, Codex, OpenCode, Even Agents) can use it: 7 curated tools, discovered on demand, with your key stored on your machine and every call going direct to GroqCloud.
What agents can do with GroqCloud
Curated for agents: the calls that matter, with schemas and descriptions written for tool use, not an endpoint dump.
groq_chat_completionSend a chat completion request. `model` is one of the available Groq models (e.g. mixtral-8x7b-32768, llama3-70b-8192). `messages` is an array of {role, content} objects.
groq_list_modelsList available models and their context windows.
groq_get_modelRetrieve metadata for a single model by id.
groq_transcribe_audioTranscribe speech to text with Whisper. Provide `url` (a public audio URL) or upload a file; `model` is whisper-large-v3 or whisper-large-v3-turbo.
groq_translate_audioTranslate spoken audio into English text with Whisper. Provide `url` or upload a file.
groq_text_to_speechSynthesize speech from text (PlayAI TTS). Returns raw audio bytes. `voice` is a voice id like Fritz-PlayAI.
groq_create_completionText completion (OpenAI-compatible). `model` is the model id; `prompt` is the input text.
Connect it in a minute
The connect flow is agent-driven: Even opens the key page in its own browser and collects the key through a secure native field. It never passes through the chat.
- Paste the prompt below into any agent running inside Even, or click Connect in Even's catalog.
- Sign in to the GroqCloud console and go to the API Keys page.
- Click 'Create API Key', give it a name, and copy the key.
- Paste the key into Even's secure field. Even verifies it and your agents are live.
Connect GroqCloud to Even: call connect_begin("groq") on the even-connect MCP and walk me through it.
Send a chat prompt to Groq's Mixtral model and transcribe a voice message using Whisper.
More Even Connect services
One MCP server, a handful of meta-tools, every service below. Agents search for the right tool at run time, so context stays lean.