The GroqCloud connector lets your AI agent act in each user's GroqCloud account. Each user connects their own GroqCloud access token once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 12 tools.
- Tools
- 12
- What they doRead · write · destructive
- 7 · 3 · 27 read3 write2 destructive
- Users sign in with
- Access token
Setup
Install the SDK
Terminal window npm install @scalekit-sdk/node dotenvTerminal window pip install scalekit-sdk-python python-dotenvSet your credentials
Add your Scalekit credentials to your
.envfile. Find values in app.scalekit.com > Developers > API Credentials..env SCALEKIT_ENVIRONMENT_URL=<your-environment-url>SCALEKIT_CLIENT_ID=<your-client-id>SCALEKIT_CLIENT_SECRET=<your-client-secret>Create the GroqCloud connection
In AgentKit > Connections, create a GroqCloud connection. The name you give it is the
connection_nameyour code passes. See Configure connections.Authorize a user and make your first call
quickstart.mts import { ScalekitClient } from '@scalekit-sdk/node'import 'dotenv/config'import { createInterface } from 'node:readline/promises'const scalekit = new ScalekitClient(process.env.SCALEKIT_ENVIRONMENT_URL,process.env.SCALEKIT_CLIENT_ID,process.env.SCALEKIT_CLIENT_SECRET,)const actions = scalekit.actionsconst connector = 'groq'const identifier = 'user_123'// Generate an authorization link for the userconst { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })console.log('Authorize GroqCloud:', link)const rl = createInterface({ input: process.stdin, output: process.stdout })await rl.question('Press Enter after authorizing...')rl.close()// Make your first callconst result = await actions.executeTool({connector,identifier,toolName: 'groq_batches_list',toolInput: {},})console.log(result)Terminal window npx tsx quickstart.mtsquickstart.py import osfrom scalekit import ScalekitClientfrom dotenv import load_dotenvload_dotenv()scalekit_client = ScalekitClient(env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),client_id=os.getenv("SCALEKIT_CLIENT_ID"),client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),)actions = scalekit_client.actionsconnection_name = "groq"identifier = "user_123"# Generate an authorization link for the userlink_response = actions.get_authorization_link(connection_name=connection_name,identifier=identifier,)print("Authorize GroqCloud:", link_response.link)input("Press Enter after authorizing...")# Make your first callresult = actions.execute_tool(tool_input={},tool_name="groq_batches_list",connection_name=connection_name,identifier=identifier,)print(result)Terminal window python quickstart.pyEach user opens the link once and enters their GroqCloud credentials there. See Authorize a user for the full flow and statuses.
Tools
Pass the exact name toexecute_toolgroq_batch_getGet a batch job's status and progress.Read-onlyGet Batch
Get a batch job's status and progress. Returns id, status, input_file_id, output_file_id, error_file_id, request_counts (total, completed, failed) and timestamps. Use groq_file_content_get on output_file_id to read results once status is completed.
Inputs
batch_idstringrequired- ID of the batch. Example: batch_01jh6xa7reempvjyh6n3yst2zw.
groq_batches_listList your organization's batch jobs.Read-onlyList Batches
List your organization's batch jobs. Returns data with each batch's id, status, input_file_id, output_file_id, request_counts and timestamps. Use groq_batch_get for one batch.
Inputs
This tool takes no inputs.
groq_file_content_getDownload the contents of a file, such as a batch's JSONL output or error file.Read-onlyGet File Content
Download the contents of a file, such as a batch's JSONL output or error file. Returns the raw file content (JSON Lines for batch files). Use this after groq_batch_get shows an output_file_id.
Inputs
file_idstringrequired- ID of the file to download. Example: file_01jh6x76wtemjr74t1fh0faj5t.
groq_file_getGet one file's metadata.Read-onlyGet File
Get one file's metadata. Returns id, object, bytes, created_at, filename and purpose. Use groq_file_content_get for its contents.
Inputs
file_idstringrequired- ID of the file. Example: file_01jh6x76wtemjr74t1fh0faj5t.
groq_files_listList the files uploaded to your GroqCloud organization, such as batch input and output files.Read-onlyList Files
List the files uploaded to your GroqCloud organization, such as batch input and output files. Returns data with each file's id, filename, purpose, bytes and created_at. Use groq_file_get for one file and groq_file_content_get to read it.
Inputs
This tool takes no inputs.
groq_model_getGet details of one GroqCloud model.Read-onlyGet Model
Get details of one GroqCloud model. Returns id, object, created, owned_by, active, context_window and max_completion_tokens. Use groq_models_list to see every model.
Inputs
modelstringrequired- ID of the model. Example: llama-3.3-70b-versatile.
groq_models_listList the models available to your GroqCloud organization.Read-onlyList Models
List the models available to your GroqCloud organization. Returns data with each model's id, owned_by, active status, context_window and max_completion_tokens. Use this to pick a model ID for groq_chat_completion_create. Use groq_model_get for one model.
Inputs
This tool takes no inputs.
groq_batch_createCreate a batch job that runs many chat completion requests from an uploaded JSONL file asynchronously, at a discount.WriteCreate Batch
Create a batch job that runs many chat completion requests from an uploaded JSONL file asynchronously, at a discount. Returns the batch with id, status (validating at first), input_file_id, completion_window, created_at and request_counts. The input file must already be uploaded with purpose batch (in the GroqCloud console or API). Track it with groq_batch_get.
Inputs
completion_windowstringrequired- Time frame for processing, from 24h to 7d. Example: 24h.
input_file_idstringrequired- ID of the uploaded JSONL file of requests, from groq_files_list. Example: file_01jh6x76wtemjr74t1fh0faj5t.
metadataobject- Custom metadata for the batch. Example: {"job": "nightly-eval"}
groq_chat_completion_createGenerate a model reply to a conversation on GroqCloud's fast inference, with optional tool calling, JSON or structured output, reasoning and web search for compound models.WriteCreate Chat Completion
Generate a model reply to a conversation on GroqCloud's fast inference, with optional tool calling, JSON or structured output, reasoning and web search for compound models. Returns id, model, choices (each with message content, tool_calls and finish_reason), usage token counts and timing information. Use this for chat-style prompts and tool use. Use groq_response_create for the OpenAI Responses API shape.
Inputs
messagesarrayrequired- Conversation so far, oldest first. Each message has a role (system, user, assistant or tool) and content; tool results also need tool_call_id. Example: [{"role": "system", "content": "You are a concise assistant."}, {"role": "user", "content": "Summarize the benefits of LPUs in two sentences."}]
modelstringrequired- ID of the model to use. Get IDs from groq_models_list or https://console.groq.com/docs/models. Example: llama-3.3-70b-versatile.
citation_optionsstring- Whether the model cites documents or search results. Default enabled. Example: enabled.one of
enableddisabled compound_customobject- Custom model and tool configuration for Groq Compound systems. Example: {"tools": {"enabled_tools": ["web_search"]}}
documentsarray- Documents the model can cite, each an object with text (and optional id). Example: [{"id": "doc1", "text": "GroqCloud runs open models on LPUs."}]
frequency_penaltynumber- Penalty from -2 to 2 for tokens by how often they already appeared. Default 0. Example: 0.5.
include_reasoningboolean- Include a reasoning field in the reply for reasoning models. Example: false.
max_completion_tokensinteger- Maximum number of tokens to generate. Example: 1024.
parallel_tool_callsboolean- Allow several tool calls in one turn. Default true. Example: true.
presence_penaltynumber- Penalty from -2 to 2 for tokens that already appeared. Default 0. Example: 0.5.
reasoning_effortstring- Reasoning effort for reasoning models; the values each model accepts differ. Example: low.one of
nonedefaultminimallowmediumhighxhighmax reasoning_formatstring- How reasoning appears in the reply: hidden, raw (inline in content) or parsed (separate reasoning field). Do not combine with include_reasoning. Example: parsed.one of
hiddenrawparsed response_formatobject- Output format. {"type": "json_object"} for JSON mode, or {"type": "json_schema", "json_schema": {...}} for structured output on supported models. Example: {"type": "json_object"}
search_settingsobject- Web search settings for compound models, such as include_domains, exclude_domains and country. Example: {"include_domains": ["groq.com"], "country": "united states"}
seedinteger- Seed for best-effort deterministic sampling. Example: 42.
service_tierstring- Processing tier: auto, on_demand, flex or performance. Example: auto.one of
autoon_demandflexperformance stoparray- Up to 4 sequences that stop generation. Example: ["\n\n", "END"]
temperaturenumber- Sampling temperature from 0 to 2. Default 1; lower is more focused. Example: 0.2.
tool_choicestring- Whether the model calls a tool: none, auto (default when tools are given) or required. Example: auto.one of
noneautorequired toolsarray- Functions the model may call, each {"type": "function", "function": {name, description, parameters JSON Schema}}. Example: [{"type": "function", "function": {"name": "get_weather", "description": "Get weather for a city", "parameters": {"type": "object", "properties": {"city": {"...
top_pnumber- Nucleus sampling probability mass from 0 to 1. Default 1. Change this or temperature, not both. Example: 0.9.
userstring- Your identifier for the end user, for abuse monitoring. Example: user-1234.
groq_response_createGenerate a model response with the OpenAI-compatible Responses API (beta) on GroqCloud.WriteCreate Response
Generate a model response with the OpenAI-compatible Responses API (beta) on GroqCloud. Returns id, model, status, output items (messages, reasoning and function calls), output_text and usage. Use this when your code expects the Responses API shape. Use groq_chat_completion_create for chat messages. Responses are not stored.
Inputs
inputstringrequired- Text input to the model. Example: Write a haiku about fast inference.
modelstringrequired- ID of the model to use. Get IDs from groq_models_list or https://console.groq.com/docs/models. Example: llama-3.3-70b-versatile.
instructionsstring- System or developer message inserted first in the model's context. Example: Answer in one short paragraph.
max_output_tokensinteger- Upper bound on generated tokens, including reasoning tokens. Example: 512.
metadataobject- Up to 16 custom key-value pairs. Example: {"ticket": "T-1001"}
parallel_tool_callsboolean- Allow several tool calls at once. Default true. Example: true.
reasoningobject- Reasoning configuration for reasoning models, for example {"effort": "low"}. Example: {"effort": "low"}
service_tierstring- Processing tier: auto, default or flex. Default auto. Example: auto.one of
autodefaultflex temperaturenumber- Sampling temperature from 0 to 2. Default 1. Example: 0.7.
textobject- Output format: plain text or structured JSON, as {"format": {"type": "text"}} or a json_schema format. Example: {"format": {"type": "text"}}
tool_choicestring- Whether the model calls a tool: none, auto or required. Example: auto.one of
noneautorequired toolsarray- Function tools the model may call, at most 128, each {"type": "function", "name", "description", "parameters"}. Example: [{"type": "function", "name": "get_weather", "description": "Get weather for a city", "parameters": {"type": "object", "properties": {"city": {"type": "strin...
top_pnumber- Nucleus sampling probability mass from 0 to 1. Default 1. Example: 0.9.
truncationstring- auto drops older context when the input is too long; disabled (default) returns an error. Example: disabled.one of
autodisabled userstring- Your identifier for the end user. Example: user-1234.
groq_batch_cancelCancel a batch job that is still in progress.DestructiveCancel Batch
Cancel a batch job that is still in progress. Returns the batch with status cancelling, then cancelled. Requests that already finished stay available in the output file.
- Idempotent
Inputs
batch_idstringrequired- ID of the batch to cancel. Example: batch_01jh6xa7reempvjyh6n3yst2zw.
groq_file_deletePermanently delete a file from your GroqCloud organization.DestructiveDelete File
Permanently delete a file from your GroqCloud organization. Returns id, object and deleted true. Use groq_files_list to find file IDs.
- Idempotent
Inputs
file_idstringrequired- ID of the file to delete. Example: file_01jh6x76wtemjr74t1fh0faj5t.
No tools match.