specification: API Commons Rate Limits
specificationVersion: '0.1'
schema: https://raw.githubusercontent.com/api-evangelist/interface-research/main/schema/api-commons.yml#/$defs/RateLimits
provider: Fireworks AI
providerId: fireworks-ai
created: '2026-05-08'
# Provenance stamped 2026-08-11: this artifact was written by the API Evangelist
# bulk sweep dated 2026-05-08, not harvested from the provider. See roadmap#35.
method: generated
modified: '2026-05-08'
reconciled: false
tags:
- AI
- LLM
- Inference
- Multimodal
- Fine-tuning
- Rate Limiting
- Quotas
- Throttling
description: >-
  Fireworks AI publishes high serverless rate limits that scale with paid
  spend, expressed primarily as RPM (requests per minute) per model, with
  separate limits for batch jobs and fine-tuning. On-demand dedicated
  deployments are bounded by provisioned GPU capacity rather than shared
  serverless limits.
notes: >-
  Per-model RPM and concurrency limits are listed on the docs.fireworks.ai
  rate-limits page; verify on reconciliation. Free-tier accounts have lower
  limits than paid postpaid accounts.
sources:
- https://docs.fireworks.ai/guides/rate-limits
- https://fireworks.ai/pricing
responseCodes:
  throttled: 429
limits:
- name: Requests Per Minute (RPM)
  scope: account
  metric: requests
  limit: see provider documentation
  notes: Per-model RPM, varies by tier and model.
- name: Concurrent Requests
  scope: account
  metric: concurrent
  limit: see provider documentation
  notes: Concurrency cap per model on serverless.
- name: Tokens Per Minute (TPM)
  scope: account
  metric: tokens
  limit: see provider documentation
  notes: Per-model TPM, varies by tier and model.
- name: Batch Inference
  scope: account
  metric: jobs
  limit: separate from sync limits
  notes: Batch runs at 50% discount and does not consume sync RPM/TPM directly.
- name: Fine-Tuning Jobs
  scope: account
  metric: concurrent_jobs
  limit: see provider documentation
  notes: Concurrency cap on parallel fine-tuning jobs.
- name: On-Demand Deployments
  scope: deployment
  metric: requests
  limit: bounded by provisioned GPU capacity
  notes: Throughput determined by GPU sizing and autoscaling configuration.
policies:
- name: Tiered Limits
  description: Limits scale up automatically with paid postpaid usage and via Enterprise agreements.
- name: Backoff Strategy
  description: Clients should implement exponential backoff with jitter and honor Retry-After.
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com