OpenRouter
25 model routes currently listed at zero price.
https://openrouter.ai/api/v1Models mentioned
inclusionai/ling-3.0-flash-vl:freenex-agi/nex-n2.5-mini:freenex-agi/nex-n2.5-pro:freeinclusionai/ling-3.0-flash-sante:freeinclusionai/ling-3.0-flash-fin:freedots-studio/dots-3-note-preview:freeliquid/lfm-2.5-2.6b:freenvidia/nemotron-3.5-lightning:freethinkingmachines/inkling-small:freepoolside/laguna-s-2.1:freethinkingmachines/inkling:freepoolside/laguna-xs-2.1:freecohere/north-mini-code:freenvidia/nemotron-3.5-content-safety:freenvidia/nemotron-3-ultra-550b-a55b:freenvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freegoogle/gemma-4-26b-a4b-it:freegoogle/gemma-4-31b-it:freegoogle/lyria-3-pro-previewgoogle/lyria-3-clip-previewnvidia/nemotron-3-super-120b-a12b:freeqwen/qwen3.8-27b:freedeepseek/deepseek-v4-flash-0731:freez-ai/glm-5.2:freeopenrouter/freeEquivalent paid value
How this was valued: Best case for the documented no-purchase free tier (20 requests/minute, 50 requests/day across all free routes; the daily cap binds) saturated by thinkingmachines/inkling:free. Its live free endpoint exposes a 1,048,576-token context and 262,144-token maximum completion; the comparison uses the current paid route for the exact model at $1.00/M input and $4.05/M output. Each request assigns 262,144 tokens to output and the remaining 786,432 context tokens to input. Model rows are alternative uses of the shared request pool and are not additive. Assumes uninterrupted saturation with no latency, availability, or fair-use loss, and assumes the paid comparator's smaller per-call context can be consumed over multiple calls. Routes lacking a suitable same-model paid comparator, the zero-price Lyria previews, and the random openrouter/free router are excluded. Accounts that have ever purchased at least $10 of credits get 1,000 requests/day instead of 50; that purchase-conditioned 20x variant is shown as a separate model_values alternative and excluded from the headline.
Limits and terms
- Requests Per Minute
- 20
- Requests Per Day Without Purchase
- 50
- Requests Per Day After 10 USD Credit Purchase
- 1,000
- Scope
- Total across free-model requests; failed requests count.
What happens to your prompts?
OpenRouter defaults are protective, but the selected upstream model provider and optional logging or data-sharing controls determine end-to-end handling.
- Plan Scope
- OpenRouter API and chat; downstream handling varies by selected model endpoint and account privacy controls.
- Prompt Retention
- OpenRouter does not retain prompts or responses by default. Optional private logging retains content for at least three months and possibly longer until deletion is requested; some processing and cache features have separate retention.
- Response Retention
- Same policy as prompts.
- Ordinary Logging
- Request metadata such as model, token counts, timestamps, cost, and latency is retained without prompt or response content.
- Model Training
- OpenRouter does not train on inputs or outputs by default. A separate opt-in permits product improvement; downstream model providers may retain or train unless endpoint policy controls exclude them.
- Product Improvement
- Optional input/output sharing is off by default and provides a usage discount when enabled. Anonymous prompt categorization may occur under a zero-data-retention arrangement.
- Human Or Operator Access
- Privately logged content is visible to the account owner or organization admins; OpenRouter says it does not access that content except where feature terms, operations, security, troubleshooting, or law require.
- Subprocessors And Routing
- Requests are sent to the selected or automatically routed model provider, whose own endpoint-specific policy applies. Zero-data-retention routing can be enforced.
- Deletion Controls
- Account owners may request deletion of privately logged prompt and response content; retention for optional features is documented separately.
- Caveat
- Privacy depends on both OpenRouter settings and the final model endpoint. OpenRouter conservatively treats an unknown provider policy as retaining and training on data.
Governing documents
- Terms Of Service
- https://openrouter.ai/terms/
- Privacy Policy
- https://openrouter.ai/privacy/
Eligibility
- Account Required
- Yes
- Payment Method Required
- No
Primary sources
Before you build with OpenRouter
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
This snapshot records 25 model IDs. Match the exact ID against the provider's live catalog before using it in code; zero-price routes and aliases can rotate while an older documentation page remains online. The recorded base endpoint is https://openrouter.ai/api/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 “Partially private”: OpenRouter defaults are protective, but the selected upstream model provider and optional logging or data-sharing controls determine end-to-end handling. 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 11 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.