Fireworks AI · none caching
NVIDIA Nemotron Nano 2 VL
NVIDIA Nemotron Nano 2 VL on Zumik: live pricing, context, and caching, routable by id or alias through one OpenAI-compatible endpoint.
Specifications
At a glance.
| Provider | Fireworks AI |
| Family | nemotronh_nano_vl_v2 |
| Released | — |
| License | Open weights |
| Context window | 131K tokens |
| Max output | — |
| Parameters | 13B |
| Modalities | text, image |
| Tool calling | No |
| Reasoning mode | No |
| Caching | none |
| Batch discount | No batch tier |
Measured by Zumik
What reuse looks like here.
Pricing, context, and capabilities for NVIDIA Nemotron Nano 2 VL are live, but it is outside the flagship set Zumik benchmarks in depth, so measured reuse, capture, and warm TTFT are not shown yet. Run a workload estimate or route it by id to start collecting traces.
Call it
Same OpenAI client, this model.
from openai import OpenAI
client = OpenAI(base_url="https://api.zumik.ai/v1", api_key="zk_live_...")
r = client.responses.create(
model="nemotron-nano-v2-12b-vl",
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseFrequently asked
NVIDIA Nemotron Nano 2 VL, answered.
How much does NVIDIA Nemotron Nano 2 VL cost?
NVIDIA Nemotron Nano 2 VL is an open-weights model routed through Fireworks AI. It is priced on the host's serverless size tier rather than a single published per-token list price, so it shows "—" here until profiled.
What is NVIDIA Nemotron Nano 2 VL's context window?
NVIDIA Nemotron Nano 2 VL supports a 131K-token context window.
Does NVIDIA Nemotron Nano 2 VL support prompt caching?
Yes. Fireworks AI uses Automatic prompt caching (serverless and dedicated) caching. In the Zumik corpus, NVIDIA Nemotron Nano 2 VL shows a median cache capture of 77% on agent workloads.
Run NVIDIA Nemotron Nano 2 VL with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.