Fireworks AI
Serverless and dedicated inference for open-source LLMs, embeddings, rerankers, and image-generation models.
Three ways to use Fireworks AI
Ask your specialist
Pull data, take actions, or answer questions with this integration, right in a conversation.
Build a workflow
Create automated workflows that trigger on events, run on a schedule, or chain multiple tools together.
Power an app
Use this integration as a data source or action layer behind a dashboard, form, or internal tool.
Supported tools
Actions your AI agents can perform with Fireworks AI.
Create Anthropic-Compatible Message
Generate a completion using the Anthropic Messages API shape.
Create Batch Inference Job
Create a batch inference job that processes a dataset of prompts asynchronously at lower cost.
Create Chat Completion
Generate a chat-style completion from an open-source LLM hosted on Fireworks (OpenAI-compatible).
Create Dataset
Create a dataset record (preceding an upload) for fine-tuning or batch inference.
Create Embeddings
Generate an embedding vector for a string or batch of strings (OpenAI-compatible).
Create Response (Responses API)
Create a model response with optional tool/MCP calling (OpenAI Responses API compatible).