Nemotron
NVIDIA's open models, tuned for throughput rather than benchmarks.
Nemotron is NVIDIA's open-weight family, built to run fast on NVIDIA hardware. The Lightning models activate only a few billion of their parameters per token and are meant for high-throughput agent workloads, and the line includes specialised members like a content-safety classifier rather than one general model stretched over every job. Several are free to call through OpenRouter.
At a glance — Nemotron 3 Super
- Cost
- $0.08 in · $0.45 out per 1M tokensBudgetFree version too
- Memory
- 262K tokens — about 400 pages
- Reads
- Text
- Can do
- Use tools (agents)
- Structured output
- Thinking mode
- Good at
- Coding: better than 36% · Agentic work: better than 24% · Overall: better than 21%
- Reliability
- 99.99% uptime, last 24h
- Released
- Mar 11, 2026
Advanced details
- API model ID
nvidia/nemotron-3-super-120b-a12b- Free version
nvidia/nemotron-3-super-120b-a12b:free- Max output
- 236K tokens
- Tokenizer
- Other
- Coding index
- 37.7
- Agentic work index
- 1.7
- Overall index
- 12.8
Providers
The same model, hosted by different companies. OpenRouter picks one per request and falls back to the next if it fails.
| Provider | Input /1M | Output /1M | Cached /1M | Max output | Uptime 24h |
|---|---|---|---|---|---|
| DekaLLM · fp8 | $0.08 | $0.45 | — | 236K | 97.80% |
| DeepInfra · bf16 | $0.085 | $0.40 | — | 16K | 99.99% |
Supported parameters
- frequency_penalty
- include_reasoning
- logit_bias
- logprobs
- max_tokens
- min_p
- presence_penalty
- reasoning
- reasoning_effort
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_logprobs
- top_p
Live from OpenRouter, refreshed hourly. Scores from Artificial Analysis.
Key info
- Pricing
- Open source
- Category
- Models
- Best for
- Expert
- Made by
- NVIDIA
- Weights
- Open
- Good for
- Throughput, and specialised jobs like safety filtering