impulse

Nvidia Nemotron Nano 9B

Open weights
API id NVIDIA-Nemotron-Nano-9B-v2
Input / 1M
$0.04
at DeepInfra
Output / 1M
$0.16
at DeepInfra
Context window
131K
tokens
Max output
131K
tokens per reply
Hosts
3
3 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.04$0.16

What it costs a month

At DeepInfra list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$24.00
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$24.96
  • Coding agent1,000 requests a day, 40K in / 2K out$57.60
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$134
Use your own numbers

Where to run it

3 hosts serve Nvidia Nemotron Nano 9B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
DeepInfraInference
NVIDIA-Nemotron-Nano-9B-v2
$0.04 / $0.16
Together AIInference
NVIDIA-Nemotron-Nano-9B-v2
$0.06 / $0.25
+54% vs headline
Fireworks AIInference
nvidia-nemotron-nano-9b-v2
$0.20 / $0.20
+186% vs headline

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 DeepInfra.

Smaller NVIDIA models

No cheaper NVIDIA model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • Command R7B
    Cohere · on Cohere Chat
    $0.0375 / $0.15
    Has every key capability
    6% less
  • Gemma 4 26B
    Google · on Darkbloom
    $0.03 / $0.165
    Has every key capability
    9% less
  • Qwen3 32B
    Alibaba Qwen · on Lambda AI
    $0.05 / $0.10
    Has every key capability
    11% less
  • Llama 4 Scout 17B 16e Instruct
    Meta · on Lambda AI
    $0.05 / $0.10
    Has every key capability
    11% less

Call it

Using DeepInfra's API.

Python
from litellm import completion

response = completion(
    model="deepinfra/NVIDIA-Nemotron-Nano-9B-v2",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Nvidia Nemotron Nano 9B cost?

On DeepInfra, Nvidia Nemotron Nano 9B costs $0.04 per million input tokens and $0.16 per million output tokens.

Which APIs offer Nvidia Nemotron Nano 9B?

Nvidia Nemotron Nano 9B runs on 3 APIs: DeepInfra, Together AI and Fireworks AI.

What is Nvidia Nemotron Nano 9B's context window?

131K tokens, with up to 131K tokens in one reply.

Is Nvidia Nemotron Nano 9B being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Nvidia Nemotron Nano 9B?

Models that cost less and keep most of what it can do: Command R7B on Cohere Chat (6% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Nvidia Nemotron Nano 9B's API model id?

Use NVIDIA-Nemotron-Nano-9B-v2 with DeepInfra. Other hosts use their own ids: nvidia-nemotron-nano-9b-v2 on Fireworks AI.

Sources

Raw catalog entry for NVIDIA-Nemotron-Nano-9B-v2 on DeepInfra
{
  "max_input_tokens": 131072,
  "max_output_tokens": 131072,
  "input_cost_per_token": 4e-8,
  "output_cost_per_token": 1.6e-7,
  "litellm_provider": "deepinfra",
  "mode": "chat",
  "supports_tool_choice": true,
  "supports_function_calling": true
}