NVIDIA
NVIDIA: Nemotron 3.5 Transcribe
transcriptionopen
Turns audio into text.
- Input
- $16.67 / M
- Context
- —
United States
NVIDIA
Nemotron and hosted open models, including embed and rerank.
- HQ
- Santa Clara
- Weights
- mixed
- Models listed
- 21
Release timeline
Latest 21. Size is context length.
Models
NVIDIA
NVIDIA: Nemotron 3.5 Embed 1B (free)
embeddings
Turns text into vectors for search.
- Input
- Free / M
- Context
- 33K
NVIDIA
NVIDIA: Nemotron 3.5 Embed 8B (free)
embeddings
Turns text into vectors for search.
- Input
- Free / M
- Context
- 33K
NVIDIA
NVIDIA: Nemotron 3.5 Rerank 8B (free)
rerank
Reorders passages by relevance to a query.
- Input
- Free / M
- Context
- 33K
NVIDIA
NVIDIA: Nemotron 3.5 Super VL
chatopen
Writes text. Use it when the answer is a paragraph, a plan, or a tool call.
- Input
- $0.150 / M
- Context
- 1.0M
NVIDIA
NVIDIA: Nemotron 3.5 Super VL (free)
chatopen
Writes text. Use it when the answer is a paragraph, a plan, or a tool call.
- Input
- Free / M
- Context
- 1.0M
NVIDIA
NVIDIA: Switchyard
router
Picks another model, or a deployment, for this request.
- Input
- Variable / M
- Context
- 1.0M
NVIDIA
NVIDIA: Nemotron 3.5 ASR Streaming Multilingual 0.6B
transcriptionopen
Turns audio into text.
- Input
- $3.33 / M
- Context
- —
NVIDIA
NVIDIA: Nemotron 3.5 Lightning
chatopen
Writes text. Use it when the answer is a paragraph, a plan, or a tool call.
- Input
- $0.070 / M
- Context
- 262K
NVIDIA
NVIDIA: Nemotron 3.5 Lightning (free)
chatopen
Writes text. Use it when the answer is a paragraph, a plan, or a tool call.
- Input
- Free / M
- Context
- 1.0M
NVIDIA
NVIDIA: Nemotron 3 Embed 1B (free)
embeddings
Turns text into vectors for search.
- Input
- Free / M
- Context
- 33K
NVIDIA
NVIDIA: Llama Nemotron Rerank VL 1B V2 (free)
rerank
Reorders passages by relevance to a query.
- Input
- Free / M
- Context
- 10K
NVIDIA
NVIDIA: Nemotron 3.5 Content Safety
reasoningopen
A chat model that spends extra steps before it answers.
- Input
- $0.200 / M
- Context
- 131K
NVIDIA
NVIDIA: Nemotron 3.5 Content Safety (free)
reasoningopen
A chat model that spends extra steps before it answers.
- Input
- Free / M
- Context
- 128K
NVIDIA
NVIDIA: Nemotron 3 Ultra
reasoningopen
A chat model that spends extra steps before it answers.
- Input
- $0.600 / M
- Context
- 262K
NVIDIA
NVIDIA: Nemotron 3 Ultra (free)
reasoningopen
A chat model that spends extra steps before it answers.
- Input
- Free / M
- Context
- 1.0M
NVIDIA
NVIDIA: Parakeet TDT 0.6B v3
transcription
Turns audio into text.
- Input
- $16.67 / M
- Context
- —
NVIDIA
NVIDIA: Nemotron 3 Nano Omni (free)
reasoningopen
A chat model that spends extra steps before it answers.
- Input
- Free / M
- Context
- 256K
NVIDIA
NVIDIA: Nemotron 3 Super
reasoningopen
A chat model that spends extra steps before it answers.
- Input
- $0.300 / M
- Context
- 1.0M
NVIDIA
NVIDIA: Llama Nemotron Embed VL 1B V2 (free)
embeddingsopen
Turns text into vectors for search.
- Input
- Free / M
- Context
- 131K
NVIDIA
NVIDIA: Nemotron 3 Nano 30B A3B
chatopen
Writes text. Use it when the answer is a paragraph, a plan, or a tool call.
- Input
- $0.060 / M
- Context
- 262K