NVIDIA: Nemotron 3.5 Lightning (free)
Freenvidia/nemotron-3.5-lightning:free
- Input / M
- $0
- Output / M
- $0
- Context
- 1M
- Max output
- 65.5K
- Listed since
- Aug 11, 2026
- Can do
- Tools · Reasoning
Reliability
Measured · signed cheapoS reports7 of 14 known outcomes answered. A rate appears at 20.
- Avg time
- 52.4 s 15 timed
- Failures
- 7 0 rate-limited
- Reports
- 15 1 cancelled or unknown
- Members
- 1 early sample
Sep 21, 2026 to Sep 23, 2026 · OpenRouter via OmniRoute. The range is a 95% interval and narrows as more members report. “Answered” means the provider responded, not that the task succeeded.
Failure breakdown
- invalid response: 1
- malformed request: 1
- transient provider: 4
- capability mismatch: 1
Where to get it
All free tiers →| Listing | Price / M | Limits | Link |
|---|---|---|---|
| OpenRouter · free routenvidia/nemotron-3.5-lightning:free | $0 | Free model routes (IDs ending in :free) are limited to 20 requests per minute. Free routes allow 50 requests per day, or 1,000 per day once the account has bought at least $10 in credits. | Open ↗ |
| OpenRouter · paid routenvidia/nemotron-3.5-lightning | $0.07 / $0.20 | Pay as you go; no free-route caps. | Open ↗ |
Free routes are served by different providers with their own data policies. Check a route's page on OpenRouter before sending private code. OpenRouter terms, checked Sep 29, 2026
About
OpenRouter descriptionNVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
Knowledge cutoff: Not reported.
Catalog data from the OpenRouter model catalog, retrieved Nov 16, 2026, 5:53 PM UTC. A listing isn't a live availability check. How we measure