NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 vs Mistral Medium 3

API pricing, benchmark indices and specs — updated 19 October 2026.

nvidia · A · Open weights

Params

31.6 B

Context

262,144

30d

1.3 M

mistralai · B · API-only

Input / 1M

$0.40

Output / 1M

$2.00

AA index

proprietary · 131.1K context

Specification comparison

Differences are highlighted; identical values are muted.

Specification	NVIDIA-Nemotron-3-Nano-30B-A3B-BF16	Mistral Medium 3
Deployment	Open weights · also via API	API-only (closed weights)
Parameters	31.6 B	n/a — API-only
Architecture	NemotronHForCausalLM	n/a — API-only
Context length	262,144	131,072
Licence	other	Proprietary
Commercial use	Unknown	Per API terms
Languages	6	n/a — API-only
Downloads 30d	1,309,484	n/a — API-only
Downloads all time	10.9 M	n/a — API-only
Quantizations on the Hub	SAFETENSORS	n/a — API-only
Gated	No	n/a — API-only
First seen on the Hub	2025-12-04	n/a — API-only
API input price / 1M tokens	$0.06	$0.40
API output price / 1M tokens	$0.24	$2.00
Est. cost per 1M input + 1M output tokens	$0.30	$2.40
Cached input / 1M tokens	—	$0.04
AA Intelligence Index	8.9	9
AA Coding Index	14.4	—
AA Agentic Index	1	—
Max output tokens	235,929	104,857
API providers	2	1
Tool calling	Yes	Yes
Reasoning mode	Yes	No

Estimated cost of 1M input + 1M output tokens via OpenRouter

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 $0.30

Mistral Medium 3 $2.40

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 is 8.0× cheaper at list price.

On RTX 4090 · 24 GB · 8K context unless noted

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 · fp16 @ 256K ctx 221.6 GB / 24 GB

❌ Won’t fit