DeepInfra
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B
deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B
What it would cost per month
- Support chatbot2,000 chats a day · no caching discount$13.80/mo
- Document Q&A1,000 questions a day · no caching discount$26.40/mo
- Coding agent300 agent steps a day · no caching discount$28.35/mo
- Content writing200 drafts a day$3.85/mo
- Data extraction20,000 records a day$30.30/mo
Typical workloads at list prices. Open one to adjust it to yours.
Pricing (per 1M tokens)
Input
$0.085
Output
$0.400
Cache Write
—
Cache Read
—
Specs
Context Window262K (262,144 tokens)
Max Output Tokens262K (262,144 tokens)
Capabilities
Vision
Function Calling
Prompt Caching
Reasoning
Computer Use
Response Schema
PDF Input