Nemotron 3 Nano 30B A3B vs Nemotron Nano 12B v2 VL vs Ministral 3 3B
Ministral 3 3B comes out ahead, 74 to 68 and 63 on our weighted score, though Nemotron 3 Nano 30B A3B is 13% cheaper per token.
NVIDIANemotron 3 Nano 30B A3B
68/100- ECI—
- Price$0.05 / $0.20
- Context262K
- NVIDIA
Nemotron Nano 12B v2 VL
63/100- ECI—
- Price$0.20 / $0.60
- Context128K
- Our pick
Mistral AIMinistral 3 3B
74/100- ECI—
- Price$0.10 / $0.10
- Context262K
Ministral 3 3B is our pick
Ministral 3 3B is the better all-round choice, scoring 74/100 against Nemotron 3 Nano 30B A3B (68) and Nemotron Nano 12B v2 VL (63). Nemotron 3 Nano 30B A3B wins on price. Nemotron Nano 12B v2 VL wins on inputs & features. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceNemotron 3 Nano 30B A3BNemotron 3 Nano 30B A3B $0.087 · Ministral 3 3B $0.10 · Nemotron Nano 12B v2 VL $0.30 per 1M tokens (3:1 blend)
- Longest contextNemotron 3 Nano 30B A3B and Ministral 3 3BNemotron 3 Nano 30B A3B 262,144 · Ministral 3 3B 262,144 · Nemotron Nano 12B v2 VL 128,000 tokens
- Widest inputsNemotron Nano 12B v2 VLNemotron 3 Nano 30B A3B: Text · Nemotron Nano 12B v2 VL: Text, Images, Video · Ministral 3 3B: Text, Images
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Nemotron 3 Nano 30B A3B | Nemotron Nano 12B v2 VL | Ministral 3 3B |
|---|---|---|---|---|
| Price | 50% | 100 | 75 | 97 |
| Inputs & features | 30% | 35 | 70 | 60 |
| Context window | 20% | 37 | 24 | 37 |
| Overall | 100% | 68/100 | 63/100 | 74/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Nemotron 3 Nano 30B A3BNVIDIA | Nemotron Nano 12B v2 VLNVIDIA | Ministral 3 3BMistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.05 (best) | $0.20 | $0.10 |
| Output | $0.20 | $0.60 | $0.10 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.087 (best) | $0.30 | $0.10 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 13 providers | Median of 3 providers | Median of 1 providers |
| Limits | |||
| Context window | 262,144 tokens (best) | 128,000 tokens | 262,144 tokens (best) |
| Max output | 262,144 tokens (best) | 128,000 tokens | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | Yes | No |
| Reasoning | Yes | Yes | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | Open | Open | OpenApache 2.0 |
| API model ID | nvidia/nemotron-3-nano-30b-a3b | nvidia/nemotron-nano-12b-v2-vl | — |
| API providers | 16 (best) | 4 | 1 |
| Released | Dec 15, 2025 | Oct 28, 2025 | Dec 2, 2025 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Nemotron 3 Nano 30B A3B$0.90
- Nemotron Nano 12B v2 VL$3.20
- Ministral 3 3B$1.20
Which should you choose?
Which is better: Nemotron 3 Nano 30B A3B, Nemotron Nano 12B v2 VL or Ministral 3 3B?
Ministral 3 3B is the better all-round choice, scoring 74/100 against Nemotron 3 Nano 30B A3B (68) and Nemotron Nano 12B v2 VL (63). Nemotron 3 Nano 30B A3B wins on price. Nemotron Nano 12B v2 VL wins on inputs & features. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Nemotron 3 Nano 30B A3B, Nemotron Nano 12B v2 VL or Ministral 3 3B?
Nemotron 3 Nano 30B A3B is cheaper at $0.05 input / $0.20 output per million tokens (median across 13 API providers; free on Nvidia). Ministral 3 3B costs $0.10 input / $0.10 output per million tokens (median across 1 API provider); Nemotron Nano 12B v2 VL costs $0.20 input / $0.60 output per million tokens (median across 3 API providers; free on Nvidia). At a typical mix of three input tokens to one output token, that is $0.087 per million tokens for Nemotron 3 Nano 30B A3B versus $0.10 for Ministral 3 3B (1.1× as much) and $0.30 for Nemotron Nano 12B v2 VL (3.4× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Nemotron 3 Nano 30B A3B has not been scored yet, Nemotron Nano 12B v2 VL has not been scored yet and Ministral 3 3B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Nemotron 3 Nano 30B A3B, Nemotron Nano 12B v2 VL and Ministral 3 3B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Nemotron 3 Nano 30B A3B and Ministral 3 3B have the largest context windows (262,144 and 262,144 tokens), against 128,000 for Nemotron Nano 12B v2 VL. Maximum output per response: Nemotron 3 Nano 30B A3B up to 262,144, Nemotron Nano 12B v2 VL up to 128,000, Ministral 3 3B up to 262,144 tokens.
Which can read images, PDFs, audio or video?
Nemotron 3 Nano 30B A3B accepts text; Nemotron Nano 12B v2 VL accepts text, images and video; Ministral 3 3B accepts text and images. Nemotron Nano 12B v2 VL handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (Apache 2.0), so you can self-host them.
Which is newer?
Nemotron 3 Nano 30B A3B is the newest, released Dec 15, 2025. Ministral 3 3B came out Dec 2, 2025; Nemotron Nano 12B v2 VL came out Oct 28, 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.
