Nemotron Super 3 120B
nvidia.nemotron-super-3-120bPricing
List prices at Amazon Bedrock, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.15 | $0.65 | |
| Batch 50% off | $0.075 | $0.325 | 50% off |
| Flex 50% off | $0.075 | $0.325 | 50% off |
| Priority 75% more | $0.263 | $1.14 | 75% more |
What it costs a month
At Amazon Bedrock list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$93.75
- RAG over documents2,000 requests a day, 8K in / 0.6K out$95.40
- Coding agent1,000 requests a day, 40K in / 2K out$219
- Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$258
Where to run it
1 host serve Nemotron Super 3 120B. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Amazon BedrockCloud nvidia.nemotron-super-3-120b | $0.15 / $0.65 | nvidia.nemotron-super-3-120b |
Show 7 more listings: regions, snapshots and variantsHide regional listings
| Amazon Bedrock | |||||||
| Mantle nvidia.nemotron-super-3-120b | $0.15 / $0.65 | nvidia.nemotron-super-3-120b | |||||
| us-gov-west-1 nvidia.nemotron-super-3-120b | $0.18 / $0.78 +20% vs headline | nvidia.nemotron-super-3-120b | |||||
| us-gov-east-1 nvidia.nemotron-super-3-120b | $0.18 / $0.78 +20% vs headline | nvidia.nemotron-super-3-120b | |||||
| us-gov-east-1 · Mantle nvidia.nemotron-super-3-120b | $0.18 / $0.78 +20% vs headline | nvidia.nemotron-super-3-120b | |||||
| us-gov-west-1 · Mantle nvidia.nemotron-super-3-120b | $0.18 / $0.78 +20% vs headline | nvidia.nemotron-super-3-120b | |||||
| us-gov us-gov.nvidia.nemotron-super-3-120b | $0.18 / $0.78 +20% vs headline | us-gov.nvidia.nemotron-super-3-120b | |||||
| eu-west-2 nvidia.nemotron-super-3-120b | $0.23 / $1.01 +55% vs headline | nvidia.nemotron-super-3-120b | |||||
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 LicenseRuntimes: 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
- 27% less
- 27% less
- 5% less
Open-weight picks
- 5% less
- 8% less
- 35% less
- 42% less
Call it
Using Amazon Bedrock's API.
from litellm import completion
response = completion(
model="bedrock/nvidia.nemotron-super-3-120b",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Nemotron Super 3 120B cost?
On Amazon Bedrock, Nemotron Super 3 120B costs $0.15 per million input tokens and $0.65 per million output tokens.
Which APIs offer Nemotron Super 3 120B?
Nemotron Super 3 120B runs on 1 API: Amazon Bedrock.
What is Nemotron Super 3 120B's context window?
256K tokens, with up to 32K tokens in one reply.
Is Nemotron Super 3 120B being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Nemotron Super 3 120B?
Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (27% less), GPT-6 Luna on OpenAI (27% less) and Mistral Small 2603 on Mistral AI (5% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Nemotron Super 3 120B's API model id?
Use nvidia.nemotron-super-3-120b with Amazon Bedrock.
Sources
Raw catalog entry for nvidia.nemotron-super-3-120b on Amazon Bedrock
{
"input_cost_per_token": 1.5e-7,
"input_cost_per_token_batches": 7.5e-8,
"input_cost_per_token_flex": 7.5e-8,
"input_cost_per_token_priority": 2.625e-7,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 256000,
"max_output_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 6.5e-7,
"output_cost_per_token_batches": 3.25e-7,
"output_cost_per_token_flex": 3.25e-7,
"output_cost_per_token_priority": 0.0000011375,
"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_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": false
}