OpenRouter
nvidia/nemotron-3.5-lightning:free
Context window1.0M tokens
Free budgetfree · 50 req/day account-wide (1,000 after a $10 purchase) tokens/mo
Requests / min20 RPM
Requests / day50 RPD
Daily :free cap is account-wide info
OpenRouter’s :free daily cap (50/day, or 1000/day once you have ever bought $10 of credits) is shared across ALL :free models on the account, not per model. Per-row rpd values here are therefore optimistic; the router’s cooldown handling absorbs the shared 429s.
Kilo Gateway
nvidia/nemotron-3.5-lightning:free
Context window1.0M tokens
Free budgetfree · 200/hr per IP tokens/mo
Rate limitsnot published
No API key required info
Routes anonymously — the catalog ships a keyless sentinel row and calls work with no account or key.
ElectronHub
nemotron-3.5-lightning
Context window1M tokens
Free budget$0.25/week shared recurring credit tokens/mo
Rate limitsnot published
Shared weekly free credits info
ElectronHub Free renews $0.25 each week (Sunday 21:00 UTC), shared across eligible non-premium models; unused weekly credit does not roll over. These are credit-backed routes, not the separate daily :free aliases. Paid top-ups are optional and not included in this allowance. Text inference was tested; other capability flags come from the provider roster.
The :free aliases need phone verification info
ElectronHub's zero-credit ":free" aliases answered 403 "To prevent abuse and high traffic on free models, phone verification is required" on September 18, 2026. The ordinary ids this catalog carries are NOT affected and were re-tested working the same day, so the :free aliases are simply not worth adding. ElectronHub's recurring grant is $0.25 credited every Sunday at 21:00 UTC plus a separate daily Neutrino allowance.
Waterfall
nemotron-3.5-lightning-free
Context window1.0M tokens
Free budgetfree · community rate limit tokens/mo
Rate limitsnot published
Free routes depend on upstream availability info
Waterfall serves -free routes at no charge with no card under unpublished community rate limits. The ten listed routes returned matching model IDs on September 15. Twelve other -free routes (gemma-4 variants, nemotron-3-ultra, content-safety, laguna-xs, north-mini-code, dots-3, glm-5.2, ling-fin) returned 503 upstream_unavailable on two attempts and are not listed; inkling routes are forbidden and Lyria routes require payment.
NaraRouter
nemotron-3.5-lightning-free
Context window1M tokens
Free budgetfree · 7M/day shared tokens/mo
Requests / min10 RPM
Tokens / day7M TPD
Daily free quota info
NaraRouter free access requires a no-card account key plus Telegram channel/link verification. The free plan is documented at 7M tokens/day and 10 req/min, with daily reset.
Gizmo
nvidia/nemotron-3.5-lightning:free
Context window1.0M tokens
Free budget1,000 free-model requests/month · shared account quota tokens/mo
Rate limitsnot published
Shared monthly free-model requests info
Gizmo Free includes 1,000 zero-cost-model API requests per calendar month, shared by account and reset on the first day UTC. Only tested :free routes are included. The chat endpoint accepts text only: tools, image/audio messages and structured output are unsupported. Six exact-model routes returned valid text with usage.cost=0 on 2026-10-03. Selected adapter chat and streaming checks also passed. Paid-model weekly credits did not bypass the account payment-method requirement. https://gizmoplatforms.com/developers?tab=docs
Get this model the moment it changes
Limits move, models get replaced, better ones launch. Premium routers see this page's data live. Free routers see last month's.
Go live · $19/yr →Use it
FreeLLMAPI is a self-hosted router you run yourself. Install it, paste in your free OpenRouter key, and nvidia/nemotron-3.5-lightning:free answers on an OpenAI-compatible endpoint at http://localhost:3001/v1. No credit card, no hosted middleman: your prompts and your provider keys never leave your machine.
Install the router (macOS, Linux, WSL)
curl -fsSL https://freellmapi.co/install.sh | bashInstall the router (Windows PowerShell)
iwr -useb https://freellmapi.co/install.ps1 | iexCall nvidia/nemotron-3.5-lightning:free with curl
curl http://localhost:3001/v1/chat/completions \
-H "Authorization: Bearer freellmapi-your-unified-key" \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia/nemotron-3.5-lightning:free",
"messages": [{"role": "user", "content": "Say hi in five words."}]
}'The same request in Python (openai)
from openai import OpenAI
client = OpenAI(
base_url="http://localhost:3001/v1",
api_key="freellmapi-your-unified-key",
)
resp = client.chat.completions.create(
model="nvidia/nemotron-3.5-lightning:free",
messages=[{"role": "user", "content": "Say hi in five words."}],
)
print(resp.choices[0].message.content)The router answers on /v1/chat/completions and every other OpenAI surface, plus the Anthropic Messages API, so existing clients need only a new base_url. Swap the model id for auto and the router picks the best free model that is still under its limits. Full reference: docs/api.md.