nemotron-nano-v2-12b
by NVIDIAChatunverified match
NVIDIA Nemotron Nano v2 12B is a 12-billion-parameter multimodal reasoning model designed for advanced video understanding, document intelligence, and visual reasoning, built with a hybrid Transformer-Mamba architecture for high efficiency and low latency.
- Context
- 128K tokens
- Max output
- 128,000 tokens
- Released
- 2025-10-31
- Weights
- Closed
nvidia/nemotron-nano-v2-12b
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2025-10-31
- Weights
- Closed
- Input
- Text, Image
- Output
- Text
- Context window
- 128,000 max across endpoints
- Max output
- 128,000
- Providers
- 0 + 1 gateway, not counted as providers
- Epoch Capabilities Index
- not evaluated
- Direct price range
- $0.24 in at Cortecs, via gateway, fees not verified
More details
- Last updated
- 2025-10-31
- Knowledge cutoff
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel toolsunknown
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt cachingunknown
- Web searchunknown
- Computer useunknown
- System messagesunknown
- Assistant prefillunknown
- Temperature
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs nemotron-nano-v2-12b |
|---|---|---|---|---|---|
| MiniMax M1MiniMax | $0.319 | $0.132 | $1.25 | 1M | +0% |
| UncensoredCognitive Computations | $0.317 | $0.20 | $0.90 | 128K | −0% cheaper |
| Llama 3.1 70B EuryaleSao10K | $0.315 | $0.306 | $0.357 | 20.5K | −1% cheaper |
| Qwen3 VL 235B A22B InstructAlibaba (Qwen) | $0.313 | $0.20 | $0.88 | 131K | −1% cheaper |
| Qwen3 VL InstructAlibaba (Qwen) | $0.313 | $0.20 | $0.88 | 262K | −1% cheaper |
| deepseek-v3.1-terminusDeepSeek | $0.325 | $0.25 | $0.70 | 164K | +2% |
| Anubis 70B v1TheDrummer | $0.31 | $0.31 | $0.31 | 65.5K | −2% cheaper |
| Anubis 70B v1.1TheDrummer | $0.31 | $0.31 | $0.31 | 32K | −2% cheaper |
More from NVIDIA
Newest NVIDIA models in the catalogue. All NVIDIA models
| Model | Released | Context | Listed price |
|---|---|---|---|
| Nemotron 3.5 Super VL 120B A12B | 2026-10-15 | 1.05M | from $0.10 |
| Switchyard | 2026-09-21 | 1M | unpriced |
| Nemotron 3.5 ASR Streaming Multilingual 0.6B | 2026-08-13 | — | unpriced |
| Nemotron 3.5 Lightning 30B A3B | 2026-08-11 | 262K | from $0.025 |
| Nemotron 3 Nano Omni 30B TEE | 2026-07-23 | 131K | from $0.0245 |
| Nemotron 3 Embed 1B | 2026-07-16 | 32.8K | unpriced |
| Nemotron 3 Ultra 550B A55B | 2026-06-04 | 1M | from $0.50 |
| Nemotron 3.5 Content Safety | 2026-06-04 | 128K | from $0.05 |
Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model