Fireworks AI
$1 for new accounts; it does not recur.
https://api.fireworks.ai/inference/v1Models mentioned
The offer covers a dynamic catalog, provider-selected route, or model class without stable model IDs in this snapshot.
Equivalent paid value
How this was valued: Face value of the one-time signup credit. No period normalization is shown because the public offer does not state an expiry.
Limits and terms
- Signup Credit USD
- 1
- Recurrence
- No
- Caveat
- This is a small promotional signup credit, not a recurring free tier. Self-serve accounts moved to prepaid billing on 2026-07-01 and service suspends after balance depletion until payment.
What happens to your prompts?
Open-model requests are transient and no-training by default, but stored-response and proprietary partner routes can differ.
- Plan Scope
- Fireworks AI open-model inference and Responses API; proprietary model partners, explicit logging opt-ins, and advanced features can differ.
- Prompt Retention
- Open-model prompts and generations exist only in volatile memory for the request by default; prompt caches may remain in volatile memory for several minutes. Responses API stores full conversation data for 30 days when store=true, which is the default.
- Response Retention
- Same default ZDR for ordinary inference and 30-day stored conversation policy for Responses API.
- Ordinary Logging
- Token counts and service-delivery metadata are logged without content under ZDR. FireOptimizer and similar advanced features can collect content only after explicit opt-in.
- Model Training
- Fireworks does not log or store open-model prompt or generation data for training without explicit opt-in; proprietary model partner terms must be checked separately.
- Product Improvement
- Metadata can support service delivery and improvement, while content use requires an explicit logging or feature opt-in under the published open-model policy.
- Human Or Operator Access
- Default open-model payloads are not written to persistent storage. Stored Responses conversations and opted-in feature data can be accessed for service, support, security, and legal purposes.
- Subprocessors And Routing
- Fireworks hosts open models and may offer partner models under separate model-provider terms; its subprocessors are documented through the trust center.
- Deletion Controls
- Responses users can set store=false or immediately delete a stored response by ID; otherwise conversation data expires after 30 days.
- Caveat
- “ZDR by default” does not describe the Responses API default, which is store=true. Always set store=false when using Responses and review proprietary-model terms.
Governing documents
- Terms Of Service
- https://fireworks.ai/terms-of-service
- Privacy Policy
- https://fireworks.ai/privacy-policy
Primary sources
Before you build with Fireworks AI
Read the classification narrowly
This record has current first-party evidence for some zero-cost hosted inference. The label describes the bounded offer supported by evidence on 2026-09-19; it does not guarantee permanence, production suitability, uptime, latency, model quality, or access from every region.
Resolve the live model route
No stable model ID is recorded. The offer may use a dynamic catalog, a provider-selected route, or a model class, so resolve the current machine-readable ID before writing a fixed production configuration. The recorded base endpoint is https://api.fireworks.ai/inference/v1, but the provider's current API reference remains authoritative for paths, authentication, and request shape.
Confirm account and billing boundaries
The public evidence does not settle whether an account is required. Confirm the signed-in flow before treating anonymous or credential-free access as available. The payment-card requirement is conditional or not clearly documented. Treat signup friction and billing exposure as unresolved until the account flow confirms them. The equivalent paid value shown here prices a documented allowance where possible; it is not cash, guaranteed savings, or protection from overage.
Re-read the prompt policy for your plan
This record classifies the reviewed handling as “Partially private”: Open-model requests are transient and no-training by default, but stored-response and proprietary partner routes can differ. Provider policies can distinguish free, paid, enterprise, opted-in, and feature-specific traffic, so verify the governing terms for the exact account and route that will receive your data.
Follow the evidence, then re-check it
The record links 8 first-party sources covering the offer, catalog, limits, pricing, terms, privacy, or adoption evidence available to the audit. Prefer the newest governing document or live catalog when sources disagree, and submit a correction when a provider changes a material term.
Match the quota to the workload shape
Translate the published allowance into the traffic pattern you actually expect instead of comparing headline totals alone. A daily token pool can look generous while a low requests-per-minute or concurrency ceiling blocks interactive bursts; a high request limit can still fail a long-context job when input, output, or per-request tokens are capped. Separate prompt tokens from generated tokens, include retries and tool calls, and test the largest realistic payload. If the provider documents more than one limit window, the tightest window at your peak load is the practical ceiling. Research, experimental, and community access can also carry eligibility or fair-use constraints that cannot be modeled as a simple number.
Plan fallback without changing the rules
A fallback should preserve more than API syntax. Confirm that the substitute route supports the required modality, context length, streaming behavior, structured output, tools, and safety controls, then compare its prompt-retention and training terms. An OpenAI-compatible request shape does not make providers operationally or contractually equivalent. Decide which errors may trigger a retry, cap retry storms, and prevent an exhausted free route from silently switching to a billable model. If deterministic output matters, record the model revision and sampling settings; rotating aliases and free-model pools can change behavior even when the endpoint remains available.
Monitor the offer as a dependency
Capture the model ID, response model field, rate-limit headers, usage fields, latency, HTTP status, and any provider request identifier for each test. Watch for authorization failures, quota exhaustion, catalog removal, policy revisions, and dashboard balance changes as separate failure modes. Re-check the provider’s live catalog and governing pages on a schedule proportionate to the workload’s importance, and keep the dated sources that supported your decision. Free capacity is especially suitable for prototypes, evaluations, fallbacks, and bounded workloads when the application can tolerate change; a production dependency still needs observability, an exit path, and an owner responsible for re-verification.
Test one complete request before scaling
Start with the smallest permitted request using the exact credential, model ID, endpoint, and account type you intend to deploy. Record the HTTP status, response headers, usage fields, latency, and any dashboard balance change. Then exercise the failure path: an invalid model, an exhausted quota, or a rate-limit response should fail clearly without silently switching to a paid route. If the provider supports streaming or tool calls, validate those features separately because a free model can expose a narrower capability set than its paid counterpart. Keep a budget ceiling outside the application whenever billing is possible, and avoid sending sensitive data until the observed route matches the reviewed data agreement.