Integration

Fireworks AI integration

Fireworks AI inference and model platform. Run chat and text completions, an Anthropic-compatible messages call and the stateful Responses API against open-source models, create embeddings and rerank documents, then manage the account side: models, dedicated deployments and their scale, datasets, supervised fine-tuning jobs, batch inference jobs, evaluation jobs and billing usage. Serverless inference and the control plane share one host but not one path prefix, so every route below is expressed against https://api.fireworks.ai. Authentication is a bearer API key.

Connect Fireworks AI How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Fireworks AI.Built from the 35 Fireworks AI tools below, on the connection you add once.

Common Fireworks AI use cases

feature verification
code completion
building chatbots
discovering models
finding dataset IDs
monitoring training
domain-specific models
semantic search systems
uploading training data
checking model capabilities

What you can do with Fireworks AI

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Dataset, 5 operations

create_datasetCreate datasetPOSTCreate Dataset.
delete_datasetDelete datasetDELETEDelete Dataset.
get_datasetGet datasetGETGet Dataset.
list_datasetsList datasetsGETLists all datasets for the account. Returns dataset metadata including IDs, states, sizes, and creation times.
upload_dataset_fileUpload dataset filePOSTUploads dataset files to Fireworks AI for fine-tuning. Returns file metadata for use in subsequent API calls.

Deployment, 5 operations

create_deploymentCreate deploymentPOSTCreate Deployment.
delete_deploymentDelete deploymentDELETEDelete Deployment.
get_deploymentGet deploymentGETGet Deployment.
list_deploymentsList deploymentsGETList Deployments.
scale_deploymentScale deploymentPATCHScale Deployment to a specific number of replicas or to zero.

Batch inference job, 4 operations

create_batch_inference_jobCreate batch inference jobPOSTCreate Batch Inference Job.
delete_batch_inference_jobDelete batch inference jobDELETEDelete Batch Inference Job.
get_batch_inference_jobGet batch inference jobGETGet Batch Inference Job.
list_batch_inference_jobsList batch inference jobsGETList Batch Inference Jobs.

Response, 4 operations

create_responseCreate responsePOSTCreate Response.
delete_responseDelete responseDELETEDelete Response.
get_responseGet responseGETGet Response.
list_responsesList responsesGETList Responses.

Evaluation job, 3 operations

create_evaluation_jobCreate evaluation jobPOSTCreate Evaluation Job.
get_evaluation_jobGet evaluation jobGETGet Evaluation Job.
list_evaluation_jobsList evaluation jobsGETList Evaluation Jobs.

Fine tuning job, 3 operations

create_fine_tuning_jobCreate fine tuning jobPOSTCreates a supervised fine-tuning job to customize a Fireworks AI model on your data. Supports efficient LoRA fine-tuning with configurable hyperparameters.
get_fine_tuning_jobGet fine tuning jobGETRetrieves detailed information about a supervised fine-tuning job. Returns full status, metrics, configuration, and result model when complete.
list_fine_tuning_jobsList fine tuning jobsGETLists all supervised fine-tuning jobs for the account. Returns job metadata including status, model, and training progress.

Account, 2 operations

get_accountGet accountGETGet Account.
list_accountsList accountsGETList Accounts.

Model, 2 operations

get_modelGet modelGETRetrieves detailed information about a specific Fireworks AI model. Returns full specifications including context length, state, kind, and supported precisions.
list_modelsList modelsGETLists all available Fireworks AI models with capabilities and specifications. Returns model IDs, context lengths, supported features, and deployment status.

Billing usage, 1 operation

get_billing_usageGet billing usageGETGet Account Usage.

Chat, 1 operation

chat_completionsChat completionsPOSTCreates chat completions using Fireworks AI models. Supports multi-turn conversations, function calling, JSON mode, reasoning, and streaming with OpenAI-compatible API format.

Completion, 1 operation

completionsCompletionsPOSTCreates text completions from prompts using Fireworks AI models. Legacy endpoint for base models - use chat_completions for instruction-tuned models.

Embedding, 1 operation

embeddingsEmbeddingsPOSTCreates vector embeddings from text using Fireworks AI embedding models. Converts text into numerical vectors for semantic search, similarity comparison, and clustering.

Message, 1 operation

create_anthropic_messageCreate anthropic messagePOSTCreate a Message.

Rerank, 1 operation

rerank_documentsRerank documentsPOSTRerank documents.

Supervised fine tuning job, 1 operation

delete_supervised_fine_tuning_jobDelete supervised fine tuning jobDELETEDelete Supervised Fine-tuning Job.

Use Fireworks AI from Claude Code, Cursor or Codex

Connect Fireworks AI in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Fireworks AI operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Fireworks AI

Create your workspace
Sign up free. Nothing to install.
Connect Fireworks AI once
Add your Fireworks AI connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Fireworks AI integration FAQ

What can you do with the Fireworks AI integration?

LiveContext exposes 35 operations on Fireworks AI, covering dataset, deployment, batch inference job and response. Common uses include feature verification, code completion and building chatbots.