Skip to main content

​
Fireworks AI

Shanone’s Fireworks AI integration gives your agent 96 tools spanning inference, model/LoRA management, on-demand deployments, fine-tuning (SFT/DPO), evaluations, and account administration.

​
Getting Started

1

Get a Fireworks AI API key

Create an API key from the Fireworks AI dashboard.
2

Add the key in Shanone

Open Integrations in the Shanone dashboard, select Fireworks AI, and paste the API key.
3

Retry your request

Once saved, shanone_execute_tool calls for fireworks_* tools will succeed.

​
Available Tools

Shanone provides 96 tools for Fireworks AI, organized into these categories:
fireworks_chat_completion, fireworks_create_completion, fireworks_create_message, fireworks_create_embedding, fireworks_rerank_documents, fireworks_list_models
fireworks_create_batch_inference_job, fireworks_list_batch_inference_jobs, fireworks_get_batch_inference_job, fireworks_delete_batch_inference_job, fireworks_create_response, fireworks_list_responses, fireworks_get_response, fireworks_delete_response
fireworks_get_model, fireworks_create_model, fireworks_update_model, fireworks_delete_model, fireworks_get_model_upload_endpoint, fireworks_validate_model_upload, fireworks_get_model_download_endpoint, fireworks_prepare_model_precision, fireworks_load_lora, fireworks_list_loras, fireworks_get_lora, fireworks_update_lora, fireworks_unload_lora
fireworks_create_deployment, fireworks_list_deployments, fireworks_get_deployment, fireworks_update_deployment, fireworks_scale_deployment, fireworks_delete_deployment, fireworks_undelete_deployment, fireworks_list_deployment_shapes, fireworks_get_deployment_shape, fireworks_list_deployment_shape_versions
fireworks_create_dataset, fireworks_upload_dataset_files, fireworks_get_dataset_upload_endpoint, fireworks_validate_dataset_upload, fireworks_get_dataset_download_endpoint, fireworks_list_datasets, fireworks_get_dataset, fireworks_update_dataset, fireworks_delete_dataset
fireworks_create_sft_job, fireworks_list_sft_jobs, fireworks_get_sft_job, fireworks_resume_sft_job, fireworks_delete_sft_job, fireworks_create_dpo_job, fireworks_list_dpo_jobs, fireworks_get_dpo_job, fireworks_get_dpo_job_metrics_file_endpoint, fireworks_resume_dpo_job, fireworks_delete_dpo_job
fireworks_create_evaluator, fireworks_get_evaluator_upload_endpoint, fireworks_validate_evaluator_upload, fireworks_get_evaluator_build_log_endpoint, fireworks_get_evaluator_source_code_endpoint, fireworks_list_evaluators, fireworks_get_evaluator, fireworks_update_evaluator, fireworks_delete_evaluator, fireworks_create_evaluation_job, fireworks_list_evaluation_jobs, fireworks_get_evaluation_job, fireworks_get_evaluation_job_log_endpoint, fireworks_delete_evaluation_job
fireworks_list_quotas, fireworks_get_quota, fireworks_update_quota, fireworks_get_billing_usage, fireworks_get_billing_summary, fireworks_query_usage_costs, fireworks_create_api_key, fireworks_list_api_keys, fireworks_delete_api_key
fireworks_create_secret, fireworks_list_secrets, fireworks_update_secret, fireworks_delete_secret, fireworks_create_user, fireworks_list_users, fireworks_get_user, fireworks_update_user, fireworks_delete_user, fireworks_get_account, fireworks_update_account
fireworks_create_router, fireworks_list_routers, fireworks_get_router, fireworks_update_router, fireworks_delete_router

​
Common Use Cases

Fast open-model inference

Run chat completions or embeddings against open-weight models without managing GPUs

Custom fine-tuning

Upload a dataset and launch an SFT or DPO fine-tuning job, then deploy the resulting model

On-demand GPU deployments

Create and scale a dedicated deployment for a model that needs consistent low latency

Cost and usage tracking

Query billing summaries and usage costs to monitor spend across projects

​
Troubleshooting

Verify the dataset finished uploading and validating first — use fireworks_validate_dataset_upload and check fireworks_get_dataset status before referencing it in a fine-tuning job.
LoRA adapters must be loaded onto a deployment running the exact base model they were fine-tuned from — check the base model on both the LoRA and the target deployment with fireworks_get_lora / fireworks_get_deployment.
These require the connected API key to belong to an account admin, and some management endpoints additionally need an account_id configured — inference-only tools work without it.