per 1M tokens
NVIDIA Nemotron 3 Nano 30B A3B
novita/nvidia/nemotron-3-nano-30b-a3b
Nemotron-3-Nano-30B-A3B is NVIDIA's compute-efficient, open-weight reasoning model built for agentic AI. Its Mixture-of-Experts design (30B total / 3.5B active) with a hybrid Mamba-2 + Transformer architecture delivers strong reasoning and tool use at a fraction of the compute required by comparable dense models. It supports a 256K context window, toggleable chain-of-thought reasoning, function calling, and structured (JSON) outputs — making it well-suited for long-context agents, coding, and math. Released under the NVIDIA Nemotron Open Model License and ready for commercial use.
Price
per 1M tokens
Providers
Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.
No provider prices yet.
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$0.25 at list price for this workload
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.05/1M | $0.2/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-10-08 | token | $0.05 | $0.2 | Not published— |
| 2026-10-09 | token | $0.05 | $0.2 | Not published— |
| 2026-10-10 | token | $0.05 | $0.2 | Not published— |
| 2026-10-11 | token | $0.05 | $0.2 | Not published— |
| 2026-10-12 | token | $0.05 | $0.2 | Not published— |
| 2026-10-13 | token | $0.05 | $0.2 | Not published— |
| 2026-10-14 | token | $0.05 | $0.2 | Not published— |
| 2026-10-15 | token | $0.05 | $0.2 | Not published— |
| 2026-10-16 | token | $0.05 | $0.2 | Not published— |
| 2026-10-17 | token | $0.05 | $0.2 | Not published— |
| 2026-10-18 | token | $0.05 | $0.2 | Not published— |
| 2026-10-19 | token | $0.05 | $0.2 | Not published— |
| 2026-10-20 | token | $0.05 | $0.2 | Not published— |
| 2026-10-21 | token | $0.05 | $0.2 | Not published— |
| 2026-10-22 | token | $0.05 | $0.2 | Not published— |
| 2026-10-23 | token | $0.05 | $0.2 | Not published— |
| 2026-10-24 | token | $0.05 | $0.2 | Not published— |
| 2026-10-25 | token | $0.05 | $0.2 | Not published— |
| 2026-10-26 | token | $0.05 | $0.2 | Not published— |
| 2026-10-27 | token | $0.05 | $0.2 | Not published— |
| 2026-10-28 | token | $0.05 | $0.2 | Not published— |
| 2026-10-29 | token | $0.05 | $0.2 | Not published— |
| 2026-10-30 | token | $0.05 | $0.2 | Not published— |
Alternatives
- Anthropic: Claude Haiku 5.5 (batch)$0.05/1M · Compare
- DeepSeek: DeepSeek V4.1 Flash (batch)$0.05/1M · Compare
- e2ee-qwen-2-5-7b-p$0.05/1M · Compare
- Gemma 3 12B$0.05/1M · Compare
- gemma-3-4b-it$0.05/1M · Compare
- google/gemma-3-12b-it$0.05/1M · Compare
Call this model
OpenRouter id novita/nvidia/nemotron-3-nano-30b-a3b. InferenceList does not send the request.
curl
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"novita/nvidia/nemotron-3-nano-30b-a3b","messages":[{"role":"user","content":"Hello"}]}'
JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "novita/nvidia/nemotron-3-nano-30b-a3b",
messages: [{ role: "user", content: "Hello" }],
}),
});
Python
import os, json, urllib.request
req = urllib.request.Request(
"https://openrouter.ai/api/v1/chat/completions",
data=json.dumps({"model": "novita/nvidia/nemotron-3-nano-30b-a3b", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())