impulse

Nemotron Nano 12B

Open weights
API id nvidia.nemotron-nano-12b-v2
Amazon Bedrock (some versions only) retires it on 30 Mar 2027 (in 132 days). 1 host keeps serving it.
Input / 1M
$0.20
at Amazon Bedrock
Output / 1M
$0.60
at Amazon Bedrock
Context window
128K
tokens
Max output
8K
tokens per reply
Hosts
1
7 listings
Released
-
date not published

Pricing

List prices at Amazon Bedrock, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.20$0.60
Batch
50% off
$0.10$0.30
Flex
50% off
$0.10$0.30
Priority
75% more
$0.35$1.05

What it costs a month

At Amazon Bedrock list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$105
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$118
  • Coding agent1,000 requests a day, 40K in / 2K out$276
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$312
Use your own numbers

Where to run it

1 host serve Nemotron Nano 12B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
nvidia.nemotron-nano-12b-v2
$0.20 / $0.60
Retires 30 Mar 2027
Show 6 more listings: regions, snapshots and variants
Amazon Bedrock
Mantle
nvidia.nemotron-nano-12b-v2
$0.20 / $0.60
Retires 30 Mar 2027
us-gov-west-1
nvidia.nemotron-nano-12b-v2
$0.24 / $0.72
+20% vs headline
Retires 30 Mar 2027
us-gov-east-1
nvidia.nemotron-nano-12b-v2
$0.24 / $0.72
+20% vs headline
Retires 30 Mar 2027
us-gov-east-1 · Mantle
nvidia.nemotron-nano-12b-v2
$0.24 / $0.72
+20% vs headline
us-gov-west-1 · Mantle
nvidia.nemotron-nano-12b-v2
$0.24 / $0.72
+20% vs headline
us-gov
us-gov.nvidia.nemotron-nano-12b-v2
$0.24 / $0.72
+20% vs headline
Retires 30 Mar 2027

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
TextImages
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 Amazon Bedrock.

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
    33% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    33% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    13% less

Open-weight picks

  • Mistral Small 2603
    Mistral AI · on Mistral AI
    $0.15 / $0.60
    Has every key capability
    13% less
  • Qwen3.8 27B
    Alibaba Qwen · on EmpirioLabs AI
    $0.17 / $0.50
    Has every key capability
    16% less
  • Nemotron 3.5 Super VL
    NVIDIA · on Kyma API
    $0.081 / $0.472
    Has every key capability
    40% less
  • Gemma 4 31B IT
    Google · on W&B Inference
    $0.10 / $0.34
    Has every key capability
    47% less

Call it

Using Amazon Bedrock's API.

Python
from litellm import completion

response = completion(
    model="bedrock/nvidia.nemotron-nano-12b-v2",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Nemotron Nano 12B cost?

On Amazon Bedrock, Nemotron Nano 12B costs $0.20 per million input tokens and $0.60 per million output tokens.

Which APIs offer Nemotron Nano 12B?

Nemotron Nano 12B runs on 1 API: Amazon Bedrock.

What is Nemotron Nano 12B's context window?

128K tokens, with up to 8K tokens in one reply.

Is Nemotron Nano 12B being retired?

Amazon Bedrock (some versions only) retires it on 30 Mar 2027. 1 host keeps serving it.

What are cheaper alternatives to Nemotron Nano 12B?

Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (33% less), GPT-6 Luna on OpenAI (33% less) and Mistral Small 2603 on Mistral AI (13% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Nemotron Nano 12B's API model id?

Use nvidia.nemotron-nano-12b-v2 with Amazon Bedrock.

Sources

Raw catalog entry for nvidia.nemotron-nano-12b-v2 on Amazon Bedrock
{
  "deprecation_date": "2027-03-30",
  "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html",
  "input_cost_per_token": 2e-7,
  "input_cost_per_token_batches": 1e-7,
  "input_cost_per_token_flex": 1e-7,
  "input_cost_per_token_priority": 3.5e-7,
  "litellm_provider": "bedrock_converse",
  "max_input_tokens": 128000,
  "max_output_tokens": 8000,
  "mode": "chat",
  "output_cost_per_token": 6e-7,
  "output_cost_per_token_batches": 3e-7,
  "output_cost_per_token_flex": 3e-7,
  "output_cost_per_token_priority": 0.00000105,
  "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
  "supports_audio_input": false,
  "supports_function_calling": true,
  "supports_response_schema": true,
  "supports_system_messages": true,
  "supports_vision": true
}