Nebius Token Factory
$1 for new accounts; it does not recur.
https://api.tokenfactory.nebius.com/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 plus convenience normalization across its stated 30-day expiry. Period figures are comparisons, not recurring allowances.
Limits and terms
- Signup Credit USD
- 1
- Expires After Days
- 30
- Recurrence
- No
What happens to your prompts?
Training is excluded, but prompts and outputs may be stored by default unless zero-data-retention mode is enabled.
- Plan Scope
- Nebius Token Factory inference and fine-tuning; speculative decoding is enabled by default unless Zero Data Retention is selected.
- Prompt Retention
- By default API prompts and outputs may be stored for speculative decoding, with no public maximum period stated in the quick guide. Enabling ZDR prevents post-request storage.
- Response Retention
- Same default speculative-decoding storage and optional ZDR as prompts.
- Ordinary Logging
- Account, billing, usage, security, and service metadata is processed under the integrated terms and DPA; ZDR applies to content rather than eliminating all metadata.
- Model Training
- Nebius states customer data is never used to train AI models. Fine-tuning data is used only for the customer's requested training.
- Product Improvement
- Stored default content is used for speculative decoding to improve inference speed, not model training; ZDR opts out of that use.
- Human Or Operator Access
- Content is processed within Nebius infrastructure and may be stored under the default; the public guide does not promise zero operator access.
- Subprocessors And Routing
- Model hosting can occur in EU, Israel, or US locations shown per endpoint. Fine-tuning artifacts are stored centrally in the EU, and US processing relies on transfer mechanisms such as SCCs.
- Deletion Controls
- Users can enable ZDR in account settings to prevent storage after processing. Fine-tuning datasets, artifacts, and models follow separate customer resource controls.
- Caveat
- ZDR is opt-in and may reduce service level. Without it, input and output storage for speculative decoding has no stated maximum retention in the reviewed public guide.
Governing documents
- Terms Of Service
- https://tokenfactory.nebius.com/terms
- Data Processing Agreement
- https://tokenfactory.nebius.com/terms
Primary sources
Before you build with Nebius Token Factory
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.tokenfactory.nebius.com/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”: Training is excluded, but prompts and outputs may be stored by default unless zero-data-retention mode is enabled. 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 7 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.