# Fireworks AI integration

> Serverless and dedicated inference for open-source LLMs, embeddings, rerankers, and image-generation models.

- Authentication: apiKey

## Tools (21)

- **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).
- **Create Supervised Fine-Tuning Job**: Kick off a supervised fine-tuning (SFT) job on a base model with a training dataset.
- **Create Text Completion**: Generate a raw text completion from a prompt string (legacy OpenAI-compatible completion endpoint).
- **Delete Response**: Delete a stored model response by ID.
- **Generate Image (FLUX.1 schnell)**: Generate an image from a text prompt using FLUX.1 [schnell] FP8.
- **Generate or Edit Image (FLUX.1 Kontext)**: Generate or edit an image with FLUX.1 Kontext (async); poll for the result by request ID.
- **Get Batch Inference Job**: Retrieve status and output dataset of a batch inference job.
- **Get Billing Usage**: Break down usage and rated costs by deployment, model, API key, or custom tag.
- **Get Deployment**: Retrieve configuration and status for a single deployment.
- **Get Model**: Retrieve metadata for a single model.
- **List API Keys**: List API keys belonging to the account.
- **List Deployments**: List dedicated/on-demand deployments in an account.
- **List Models**: List all models available in an account, including Fireworks-hosted and custom uploads.
- **List Supervised Fine-Tuning Jobs**: List supervised fine-tuning jobs in an account.
- **Rerank Documents**: Rerank a set of documents against a query using a Qwen3 reranker.
- **Retrieve Response**: Retrieve a stored model response by ID.

## Related prompts

- [Draft a personalized outbound email for every new HubSpot lead](https://www.generalinput.com/prompts/draft-a-personalized-outbound-email-for-every-new-hubspot-lead.md)
- [Turn merged GitHub PRs into a plain English changelog](https://www.generalinput.com/prompts/turn-merged-github-prs-into-a-plain-english-changelog.md)
- [Turn Airtable content briefs into ready-to-share social images](https://www.generalinput.com/prompts/turn-airtable-content-briefs-into-ready-to-share-social-images.md)
- [AI-triage Typeform survey responses into HubSpot and Slack](https://www.generalinput.com/prompts/ai-triage-typeform-survey-responses-into-hubspot-and-slack.md)
- [Weekly Fireworks AI spend recap to Slack and Sheets](https://www.generalinput.com/prompts/weekly-fireworks-ai-spend-recap-to-slack-and-sheets.md)

Connect Fireworks AI in General Input: https://www.generalinput.com/apps/fireworks-ai