Traffic rank on Composite
#77 of 194
0.06% of tokens and 0.04% of requests over 30 days.
AI model
NVIDIA: Nemotron 3 Super
nvidia/nemotron-3-super-120b-a12b
NVIDIA: Nemotron 3 Super is a 1,048,576-token model served on Composite at $0.106 per million tokens in and $0.500 per million tokens out. Ranked #77 of 194 models by traffic on Composite over the last 30 days, taking 0.06% of tokens and 0.04% of requests.
Try in PlaygroundSpecifications
| Model ID | nvidia/nemotron-3-super-120b-a12b |
|---|---|
| Provider | cv11 |
| Context window | 1,048,576 tokens |
| Accepts | text |
| Returns | text |
| Input price | $0.106 per million tokens |
| Output price | $0.500 per million tokens |
| Prompt caching | Supported — cached input is billed at the provider's cache rate, on credits and plans alike |
| Thinking | Optional - see "NVIDIA: Nemotron 3 Super (Reasoning)" in the catalog to turn it on by default |
| Moderated | No |
| Cost on a monthly plan | About 1.1 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 10 (base plus 9 routing variants) |
Routing variants
The same model behind 9 alternative endpoints. Call the id directly to pin a route; the base id above picks for you.
| Route | Model ID | Provider | Price |
|---|---|---|---|
| Normal | nvidia/nemotron-3-super-120b-a12b-normal |
cv11 | $0.375 per million tokens input · $3.00 per million tokens output |
| Normal + cheapThink | nvidia/nemotron-3-super-120b-a12b-normal:cheapThink |
cv11 | $0.375 per million tokens input · $3.00 per million tokens output |
| Cheapest provider | nvidia/nemotron-3-super-120b-a12b:cheapest-provider |
DeepInfra | $0.106 per million tokens input · $0.500 per million tokens output |
| Cheapest provider + cheapThink | nvidia/nemotron-3-super-120b-a12b:cheapest-provider:cheapThink |
DeepInfra | $0.106 per million tokens input · $0.500 per million tokens output |
| cheapThink | nvidia/nemotron-3-super-120b-a12b:cheapThink |
cv11 | $0.106 per million tokens input · $0.500 per million tokens output |
| Fast | nvidia/nemotron-3-super-120b-a12b:fast |
DeepInfra | $0.106 per million tokens input · $0.500 per million tokens output |
| Fast + cheapThink | nvidia/nemotron-3-super-120b-a12b:fast:cheapThink |
DeepInfra | $0.106 per million tokens input · $0.500 per million tokens output |
| Quality | nvidia/nemotron-3-super-120b-a12b:quality |
DeepInfra | $0.106 per million tokens input · $0.500 per million tokens output |
| Quality + cheapThink | nvidia/nemotron-3-super-120b-a12b:quality:cheapThink |
DeepInfra | $0.106 per million tokens input · $0.500 per million tokens output |
Pricing
$0.106 per million tokens input · $0.500 per million tokens output
Credits pay the provider’s price plus 25%; cache hits cost less.
On a monthly plan, a typical call (8k tokens in, 1k out) uses about 1.1 plan credits, at the provider's own price.
Provider
cv11
Roleplay fit
Nemotron models are tuned by NVIDIA for instruction-following and tool use, and tend to behave predictably in structured prompts.
Context behavior
With a 1,048,576-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.
Cost for regular use
It is priced low enough for high-volume daily roleplay without the per-message cost adding up quickly.
From the provider
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
Supplied by cv11, not written by Composite.
Related models
NVIDIA: Nemotron 3.5 Super VL · NVIDIA: Nemotron 3.5 Lightning · NVIDIA: Nemotron 3.5 Content Safety