FireworksAI
Connect to FireworksAI for fast AI inference and language models.
Connectors
Choose the connector that matches your authentication method. The options below use the names shown in StackAI.
FireworksAI
API Key
FireworksAI
Connect to FireworksAI's fast LLM inference API.
Set up in FireworksAI
Sign up or log in at https://app.fireworks.ai.
Open your profile menu, go to Settings, and select API Keys in the sidebar.
Click Create API Key, give it a name, and copy the key (it is shown only once).
Set up in StackAI
Open Settings → Connections, add a connection, and select FireworksAI.
Enter the credentials and connection details in the fields below.
Save the connection and check its connection status. Select this saved connection when configuring an action or feature that uses it.
Connection fields
Endpoint Base URL
Optional / as applicable
Override to point at a dedicated Fireworks gateway instead of the shared serverless API. Must be https unless the host is an allowlisted private IP.
Health Check Model
Optional / as applicable
Model ID served by your gateway, used when its models endpoint is unavailable. Leave blank to probe GPT-OSS 120B on the hosted API.
Provider documentation: Setup reference.
Verify the connection
Check that the connection is healthy. Then run a read operation against a resource the connected account can access. A successful connection check confirms authentication; it does not guarantee permission for every action.
If access is denied, check the credential or OAuth permissions, the selected account or environment, and access to the specific resource. Update expired credentials or reconnect after permissions change.
Use an action
Add the required FireworksAI action to the workflow.
Select a connection when the action requests one.
Complete the required fields. Use the reference picker when a value comes from another workflow step.
Run the workflow and inspect the action’s output. Check the result before using it in a later step.
Actions
Chat Completion
Generate text with a FireworksAI model using chat-based completion
Inputs
Model
select (string)
No
The FireworksAI model to use for completion. Available values: Llama 4 Maverick, Llama 4 Scout, Llama 3.3 70B, DeepSeek V3, Qwen 2.5 Coder 32B. Default: accounts/fireworks/models/llama-v3p3-70b-instruct.
Messages
dict_array
No
List of messages in the conversation.
Temperature
number
No
Controls randomness in the output (0.0 to 2.0). Default: 0.7.
Max Tokens
number
No
Maximum number of tokens to generate.
Top P
number
No
Controls nucleus sampling (0.0 to 1.0).
Outputs
Content
string
The generated response content.
Finish Reason
string
Reason why the completion finished.
Prompt Tokens
number
Number of tokens in the prompt.
Completion Tokens
number
Number of tokens in the completion.
Total Tokens
number
Total number of tokens used.
Important behavior
Actions that create, update, send, or delete data can change the connected service. Review their inputs before running them. A retry can repeat an operation; consider this when configuring retries for actions that change data.
The catalog lists the fields and capabilities available in the supplied provider definition. Availability can also depend on your deployment and organization’s Feature Access settings.
Last updated
Was this helpful?

