NVIDIA · Released Apr 28, 2026Nemotron 3 Nano Omni 30B A3B Reasoning
Open Nemotron omni model combining reasoning with text, vision, and audio.
- Capability
- —No ECI score yet
- Input
- $0.25per 1M tokens
- Output
- $0.85per 1M tokens
- Context
- 256K66K max output
What it costs
- Input
- $0.25per million tokens
- Output
- $0.85per million tokens
- Blended (3:1)
- $0.40cheaper than 66% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $0.925 |
| Team assistant25M input + 5M output tokens | $10.50 |
| Production app250M input + 50M output tokens | $105.00 |
Median of 4 paid API providers on models.dev; NVIDIA also offers it free on Nvidia.
Independent benchmarks
Epoch AI has not published a Capabilities Index score for Nemotron 3 Nano Omni 30B A3B Reasoning yet.
The details
- Lab
- NVIDIA
- Released
- Apr 28, 2026
- Context window
- 256,000 tokens
- Max output
- 65,536 tokens
- Inputs
- Text, Images, Audio, Video
- Output
- Text
- Reasoning
- Thinking budget
- Tool calling
- Yes
- Structured output
- Yes
- Weights
- Open weights
- API model ID
nvidia/nemotron-3-nano-omni-30b-a3b-reasoningon Nvidia- Availability
- 8 API providerslisted on models.dev
More from NVIDIA
About Nemotron 3 Nano Omni 30B A3B Reasoning
How much does Nemotron 3 Nano Omni 30B A3B Reasoning cost?
Nemotron 3 Nano Omni 30B A3B Reasoning costs $0.25 input / $0.85 output per million tokens (median across 4 API providers; free on Nvidia). At a 3:1 input-to-output mix that is $0.40 per million tokens, cheaper than 66% of the 360 priced models we track.
What is the context window of Nemotron 3 Nano Omni 30B A3B Reasoning?
Nemotron 3 Nano Omni 30B A3B Reasoning accepts up to 256,000 tokens per request and can write up to 65,536 tokens in one response.
How good is Nemotron 3 Nano Omni 30B A3B Reasoning?
Epoch AI has not published a Capabilities Index score for Nemotron 3 Nano Omni 30B A3B Reasoning yet.
Is Nemotron 3 Nano Omni 30B A3B Reasoning open source?
Yes. NVIDIA publishes the weights, so it can be downloaded and self-hosted.
What inputs does Nemotron 3 Nano Omni 30B A3B Reasoning support?
Nemotron 3 Nano Omni 30B A3B Reasoning accepts text, images, audio and video and replies in text. It is a reasoning model, supports tool calling and can return structured JSON output.
When was Nemotron 3 Nano Omni 30B A3B Reasoning released?
NVIDIA released Nemotron 3 Nano Omni 30B A3B Reasoning on Apr 28, 2026.
What are the best alternatives to Nemotron 3 Nano Omni 30B A3B Reasoning?
The closest current models from other labs on capability, price and release date are Trinity Large Thinking (Arcee AI, $0.25 / $0.80), Step 3.7 Flash (StepFun, $0.185 / $1.11), Mercury Edit 2 (Inception, $0.25 / $0.75) and MiMo-V2.5-Pro (Xiaomi, $0.435 / $0.87).