impulse

Nemotron 120B A12B

Open weights
API id Nemotron-120B-A12B
Input / 1M
$0.30
at Baseten
Output / 1M
$0.75
at Baseten
Context window
-
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Baseten, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.30$0.75

What it costs a month

At Baseten list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$146
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$171
  • Coding agent1,000 requests a day, 40K in / 2K out$405
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$900
Use your own numbers

Where to run it

1 host serve Nemotron 120B A12B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
BasetenInference
Nemotron-120B-A12B
$0.30 / $0.75

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: NVIDIA Open Model License
Runtimes: TGI, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Baseten.

Smaller NVIDIA models

No cheaper NVIDIA model keeps its key capabilities.

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    52% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    52% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    36% less

Open-weight picks

  • MiniMax M3
    MiniMax · on EmpirioLabs AI
    $0.225 / $0.90
    Has every key capability
    5% less
  • Qwen3.5 397B A17B
    Alibaba Qwen · on AIHubMix
    $0.164 / $0.986
    Has every key capability
    10% less
  • Muse Glimmer 30B
    Meta · on EmpirioLabs AI
    $0.20 / $0.80
    Has every key capability
    15% less
  • Mistral Small 2603
    Mistral AI · on Mistral AI
    $0.15 / $0.60
    Has every key capability
    36% less

Call it

Using Baseten's API.

Python
from litellm import completion

response = completion(
    model="baseten/Nemotron-120B-A12B",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Nemotron 120B A12B cost?

On Baseten, Nemotron 120B A12B costs $0.30 per million input tokens and $0.75 per million output tokens.

Which APIs offer Nemotron 120B A12B?

Nemotron 120B A12B runs on 1 API: Baseten.

Is Nemotron 120B A12B being retired?

It has been retired: Baseten retired it on 16 Oct 2026.

What are cheaper alternatives to Nemotron 120B A12B?

Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (52% less), GPT-6 Luna on OpenAI (52% less) and MiniMax M3 on EmpirioLabs AI (5% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Nemotron 120B A12B's API model id?

Use Nemotron-120B-A12B with Baseten.

Sources

Raw catalog entry for Nemotron-120B-A12B on Baseten
{
  "deprecation_date": "2026-10-16",
  "input_cost_per_token": 3e-7,
  "litellm_provider": "baseten",
  "mode": "chat",
  "output_cost_per_token": 7.5e-7
}