Arli AI
A recurring no-cost API allowance with provider-published access terms.
https://api.arliai.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: Free accounts may use each model for 5 requests every 2 days (an independent per-model quota per first-party docs), capped at 12K context tokens and 1 concurrent request, so per-model best case is 2.5 requests/day with the full 12,000-token per-request envelope assigned to costlier output. This subtotal saturates that quota only for the four catalog entries that are unmodified release models with exact-model paid prices on OpenRouter (GLM-4.7, MiMo-V2.5, DeepSeek-V4-Flash-0731, Gemma-4-31B-it; snapshot 2026-08-22); the remaining 88 finetune/merge/derestricted catalog entries carry equal independent quotas but have no exact-model paid counterpart, so their value is real but unpriced. Arli AI's own paid offering is an unlimited-usage subscription with no per-token rate, so exact-model router prices are the comparison. Per-model rows are additive here because the quota is documented as independent per model. Assumes uninterrupted saturation across the two-day reset cycle.
Limits and terms
- Requests Per Model Per Two Days
- 5
- Max Context Tokens
- 12,000
- Concurrent Requests
- 1
What happens to your prompts?
Arli AI documents transient-only processing with no prompt/output storage, training, or content-based improvement.
- Plan Scope
- Arli AI hosted inference API.
- Prompt Retention
- Arli AI states prompts and inputs are used only transiently to return a response and are not logged, stored, retained, or accessed afterward.
- Response Retention
- Generated outputs receive the same zero-log treatment.
- Ordinary Logging
- Usage metadata such as request count, model, and request parameters is logged for rate limiting and usage tracking without prompt or output content.
- Model Training
- Arli AI's transient-use license does not authorize training on prompts or outputs, and its zero-log design leaves no ordinary stored content for training.
- Product Improvement
- Aggregated or non-content usage data may support operations; the terms do not authorize prompt or output use for product improvement.
- Human Or Operator Access
- Arli AI states it does not store or have access to prompt and output content beyond transient request processing.
- Subprocessors And Routing
- Open-weight or third-party models may carry model licenses and use restrictions, but the published terms describe Arli AI as the inference host rather than a changing external gateway.
- Deletion Controls
- There is no prompt history to delete under the stated zero-log design. Account and personal-data rights are governed by the privacy policy.
- Caveat
- Zero-log claims are first-party contractual statements, not an independently verified technical guarantee; metadata is still retained.
Governing documents
- Terms And Conditions
- https://www.arliai.com/terms
- Privacy Policy
- https://www.arliai.com/privacy
Eligibility
- Account Required
- Yes
- Payment Method Required
- No
Primary sources
Before you build with Arli 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.arliai.com/v1, but the provider's current API reference remains authoritative for paths, authentication, and request shape.
Confirm account and billing boundaries
An account is required, so public catalog evidence cannot by itself prove the limits, balance, or billing behavior attached to your workspace. The reviewed evidence explicitly says no payment card is required. Re-check the signup flow because eligibility and billing controls can change after the snapshot. 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 “Private”: Arli AI documents transient-only processing with no prompt/output storage, training, or content-based improvement. 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.