NVIDIA
Nemotron 3 Super
nvidia/nemotron-3-super-120b-a12bNVIDIA 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.
- Context window
- 262K
- Max output
- 236K
- Input
- Text
- Price per token
- $0
tokens
tokens per response
included in your plan
Capabilities
- Reasoning
- Tool calling
- JSON output
Reasoning effort: low, medium, high, xhigh
API
- OpenAI Chat Completions
POST /v1/chat/completions
Supported parameters
- frequency_penalty
- logit_bias
- logprobs
- max_tokens
- min_p
- presence_penalty
- reasoning
- reasoning_effort
- repetition_penalty
- response_format
- seed
- stop
- temperature
- tool_choice
- tools
- top_k
- top_logprobs
- top_p
Quickstart
Any OpenAI-compatible client works; point it at Piramyd and use your key. In a coding agent, run npx piramyd instead.
curl https://api.piramyd.cloud/v1/chat/completions \
-H "Authorization: Bearer $PIRAMYD_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia/nemotron-3-super-120b-a12b",
"messages": [
{
"role": "user",
"content": "Refactor this function to be pure: ..."
}
]
}'Also on Piramyd
Nemotron 3.5 Lightning
NVIDIA
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.
- Reasoning
- Tool calling
- JSON output
- Context
- 262K
- Output
- 131K
- Input
- Text
- Online
bge-base-en-v1.5
BAAI
English text embeddings, base (768 dimensions).
- Context
- 512
- Output
- —
- Input
- Text
- Online
bge-large-en-v1.5
BAAI
English text embeddings, large (1024 dimensions).
- Context
- 512
- Output
- —
- Input
- Text
Stop rationing your agents.
Let them finish the job.
The agents you already use, every frontier model, and a bill that doesn’t move when they work harder.
3-day trial on Solo · Card required · Cancel before day 4 and pay nothing
For AI agents
Give this link to any agent: it describes the whole API.