Zumik
Sign inSign up

NVIDIA Nemotron 3 Super 120B A12B BF16

NVIDIA Nemotron 3 Super 120B A12B BF16 on Zumik: live pricing, context, and caching, routable by id or alias through one OpenAI-compatible endpoint.

Call it through ZumikAbout Fireworks AI
$0.30
Input / 1M tokens
$0.90
Output / 1M tokens
$0.30
Cache read
256K
Context window

At a glance.

ProviderFireworks AI
Familynemotron_h
Released2026-03
LicenseOpen weights
Context window256K tokens
Max output33K tokens
Parameters120B
Modalitiestext
Tool callingYes
Reasoning modeYes
Cachingnone
Batch discountNo batch tier

What reuse looks like here.

Not yet profiled

Pricing, context, and capabilities for NVIDIA Nemotron 3 Super 120B A12B BF16 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.

Reuse economics

What you actually pay once caching works.

At a typical 55% prefix reuse, a million input tokens on NVIDIA Nemotron 3 Super 120B A12B BF16 effectively costs $0.30 instead of $0.30 - blending to roughly $0.45 with a 25% output share. There is no batch tier, so cost control here leans on caching and routing.

Estimate it for your workload
Best for
text

Route it directly by id, or let an alias pick it when it wins under policy.

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="nemotron-3-super-120b-a12b-bf16",
    input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached)   # confirm reuse

NVIDIA Nemotron 3 Super 120B A12B BF16, answered.

How much does NVIDIA Nemotron 3 Super 120B A12B BF16 cost?

NVIDIA Nemotron 3 Super 120B A12B BF16 is $0.30 per million input tokens and $0.90 per million output tokens through Zumik. Cache reads are $0.30 per million, a 0% discount on input.

What is NVIDIA Nemotron 3 Super 120B A12B BF16's context window?

NVIDIA Nemotron 3 Super 120B A12B BF16 supports a 256K-token context window with up to 33K output tokens.

Run NVIDIA Nemotron 3 Super 120B A12B BF16 with reuse measured.

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

Migration quickstartBack to catalog