Skip to content
GridRouterhome

Search

Search providers, capabilities and pages

Fireworks AI API

fireworks.ai

AI UtilitiesListed, not routed yet
Serverless and on-demand inference and fine-tuning for open models.

What it does

Inference platform for open models with serverless per-token pricing, on-demand GPU deployments and fine-tuning. Spending tiers (Tier 1-4, by credits added) set quotas and legacy postpaid monthly spend caps ($50 / $500 / $5,000 / $50,000).

Pricing

What Fireworks AI publishes for buying direct, as listed on its own pages.

Buying direct from Fireworks AI

  • Qwen3 8B$0.1 / 1M tokens

Free tier: $1 in free credits. Larger plans through sales. Fireworks AI pricing, checked Sep 29, 2026

Docs

Fireworks AI's own pages, linked as published.

Its OpenAPI document: 222 operations and rate limits
Official specOpenAPI 3.1.0 · 222 operations Spec (YAML)Provider's spec
Operations in the fireworks-ai spec
MethodPathSummaryParamsSource
GET/v1/accountsList Accounts5Spec
POST/v1/auth/refreshRefresh a session JWT before expiry with a fresh TTL.0Spec
POST/v1/creditCodes:redeemAPIs for credit codes. Redeem Credit Code0Spec
POST/v1/validateModelConfigValidate Model Config0Spec
GET/v1/accounts/{account_id}Get Account2Spec
GET/v1/accounts/{account_id}/accountUsageFilterOptionsDistinct filter values for an account/time range (serverless + dedicated; for FE, separate -yet mirrors GetAccountUsage).4Spec
GET/v1/accounts/{account_id}/auditLogsList User Audit Logs9Spec
GET/v1/accounts/{account_id}/batchInferenceJobsList Batch Inference Jobs6Spec
POST/v1/accounts/{account_id}/batchInferenceJobsCreate Batch Inference Job2Spec
GET/v1/accounts/{account_id}/batchInferenceJobs/{batch_inference_job_id}Get Batch Inference Job3Spec
DELETE/v1/accounts/{account_id}/batchInferenceJobs/{batch_inference_job_id}Delete Batch Inference Job2Spec
GET/v1/accounts/{account_id}/billing/summaryGet billing summary information for an account4Spec
POST/v1/accounts/{account_id}/usageCosts:queryQuery grouped usage cost subtotals for an account.1Spec
GET/v1/accounts/{account_id}/billingSettingsReturns the singleton BillingSettings for the given account.2Spec
PATCH/v1/accounts/{account_id}/billingSettingsUpdates the singleton BillingSettings for the given account.1Spec
GET/v1/accounts/{account_id}/billingUsageGet Account Usage7Spec
POST/v1/accounts/{account_id}/checkpoints/{checkpoint_id}:promotePromote a checkpoint to a model. The checkpoint is identified by account + snapshot ID; the trainer job ID is passed in the request body to 2Spec
GET/v1/accounts/{account_id}/clustersList Clusters6Spec
POST/v1/accounts/{account_id}/clustersCreate Cluster1Spec
GET/v1/accounts/{account_id}/clusters/{cluster_id}Get Cluster3Spec
PATCH/v1/accounts/{account_id}/clusters/{cluster_id}Update Cluster2Spec
DELETE/v1/accounts/{account_id}/clusters/{cluster_id}Delete Cluster2Spec
GET/v1/accounts/{account_id}/clusters/{cluster_id}:getConnectionInfoGet Cluster Connection Info3Spec
GET/v1/accounts/{account_id}/creditRedemptionsList Credit Redemptions6Spec
GET/v1/accounts/{account_id}/datasetsList Datasets6Spec
POST/v1/accounts/{account_id}/datasetsCreate Dataset1Spec
GET/v1/accounts/{account_id}/datasets/{dataset_id}Get Dataset3Spec
PATCH/v1/accounts/{account_id}/datasets/{dataset_id}Update Dataset2Spec
DELETE/v1/accounts/{account_id}/datasets/{dataset_id}Delete Dataset2Spec
GET/v1/accounts/{account_id}/datasets/{dataset_id}:getDownloadEndpointGet Dataset Download Endpoint4Spec
POST/v1/accounts/{account_id}/datasets/{dataset_id}:getUploadEndpointGet Dataset Upload Endpoint2Spec
POST/v1/accounts/{account_id}/datasets/{dataset_id}:splitDatasetGateway_SplitDataset2Spec
POST/v1/accounts/{account_id}/datasets/{dataset_id}:validateUploadValidate Dataset Upload2Spec
GET/v1/accounts/{account_id}/deployedModelsList LoRAs6Spec
POST/v1/accounts/{account_id}/deployedModelsLoad LoRA2Spec
GET/v1/accounts/{account_id}/deployedModels/{deployed_model_id}Get LoRA3Spec
PATCH/v1/accounts/{account_id}/deployedModels/{deployed_model_id}Update LoRA2Spec
DELETE/v1/accounts/{account_id}/deployedModels/{deployed_model_id}Unload LoRA2Spec
GET/v1/accounts/{account_id}/deploymentShapesList Deployment Shapes7Spec
POST/v1/accounts/{account_id}/deploymentShapesCRUD APIs for deployment shape. Create Deployment Shape2Spec

Showing 40 of 222 operations; the full list is in the spec.

Rate limits

Spend-tier based quotas; serverless TPM adaptive limits Without a published limit GridRouter paces conservatively (1 call per second).

Sources for this page (3)