Skip to content
For the complete documentation index, see llms.txt. This page is also available as Markdown.

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.

Connector
Authentication

FireworksAI

API Key

FireworksAI

Connect to FireworksAI's fast LLM inference API.

Set up in FireworksAI

  1. Sign up or log in at https://app.fireworks.ai.

  2. Open your profile menu, go to Settings, and select API Keys in the sidebar.

  3. Click Create API Key, give it a name, and copy the key (it is shown only once).

Set up in StackAI

  1. Open Settings → Connections, add a connection, and select FireworksAI.

  2. Enter the credentials and connection details in the fields below.

  3. Save the connection and check its connection status. Select this saved connection when configuring an action or feature that uses it.

Connection fields

StackAI field
Required
What to enter

API Key

Yes

Your FireworksAI API key. Provider instructions.

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

  1. Add the required FireworksAI action to the workflow.

  2. Select a connection when the action requests one.

  3. Complete the required fields. Use the reference picker when a value comes from another workflow step.

  4. 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

Field
Type
Required
Description

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

Field
Type
Description

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?