Fireworks AI · none caching

NVIDIA Nemotron 3 Nano Omni 30B A3B

NVIDIA Nemotron 3 Nano Omni 30B A3B on Zumik: live pricing, context, and caching, routable by id or alias through one OpenAI-compatible endpoint.

Input / 1M tokens
Output / 1M tokens
Cache read
262K
Context window

Specifications

At a glance.

ProviderFireworks AI
Familynemotron
Released
LicenseOpen weights
Context window262K tokens
Max output
Parameters30B
Modalitiestext
Tool callingNo
Reasoning modeNo
Cachingnone
Batch discountNo batch tier

Measured by Zumik

What reuse looks like here.

Not yet profiled

Pricing, context, and capabilities for NVIDIA Nemotron 3 Nano Omni 30B A3B 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.

python
from openai import OpenAI

client = OpenAI(base_url="https://api.zumik.ai/v1", api_key="zk_live_...")

r = client.responses.create(
    model="nvidia-nemotron-3-nano-omni-30b-a3b",
    input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached)   # confirm reuse

Frequently asked

NVIDIA Nemotron 3 Nano Omni 30B A3B, answered.

How much does NVIDIA Nemotron 3 Nano Omni 30B A3B cost?

NVIDIA Nemotron 3 Nano Omni 30B A3B 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 3 Nano Omni 30B A3B's context window?

NVIDIA Nemotron 3 Nano Omni 30B A3B supports a 262K-token context window.

Does NVIDIA Nemotron 3 Nano Omni 30B A3B support prompt caching?

Yes. Fireworks AI uses Automatic prompt caching (serverless and dedicated) caching. In the Zumik corpus, NVIDIA Nemotron 3 Nano Omni 30B A3B shows a median cache capture of 78% on agent workloads.

Run NVIDIA Nemotron 3 Nano Omni 30B A3B with reuse measured.

Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.