NVIDIA Nemotron Nano 12B v2 VL BF16

Models

Model details

Model
nvidia.nemotron-nano-12b-v2
Provider
amazon-bedrock
API
bedrock-converse-stream
Base URL
https://bedrock-runtime.us-east-1.amazonaws.com
Input
text, image
Reasoning
No
Context window
128,000
Max tokens
4,096
Show configuration
{
  "providers": {
    "amazon-bedrock": {
      "apiKey": "YOUR_API_KEY",
      "models": [
        {
          "id": "nvidia.nemotron-nano-12b-v2",
          "name": "NVIDIA Nemotron Nano 12B v2 VL BF16",
          "reasoning": false,
          "input": [
            "text",
            "image"
          ],
          "contextWindow": 128000,
          "maxTokens": 4096,
          "cost": {
            "input": 0.2,
            "output": 0.6,
            "cacheRead": 0,
            "cacheWrite": 0
          }
        }
      ],
      "api": "bedrock-converse-stream",
      "baseUrl": "https://bedrock-runtime.us-east-1.amazonaws.com"
    }
  }
}

Pricing

USD per million tokens. A tier is selected from the total input tokens in each request and applies to that entire request.

Pricing rates for NVIDIA Nemotron Nano 12B v2 VL BF16
Request inputInputOutputCache readCache write
All requests$0.2$0.6$0$0

Session cost calculator

Estimate the requests made during an agent session. A user turn can make several model calls while using tools, so costs are calculated per model request.

Session shape
Rounded median shapes from recent Pi agent sessions.
Warm-request cache reuse
Effective token reuse combines partial hits and occasional complete misses.
Estimated session$0.00
Uncached input
Cache reads
Uncached prefixes
Cache writes
Output
Without caching

The first request starts cold unless marked otherwise. Output is billed separately from context growth because reasoning tokens are not always retained. This remains a directional estimate: providers differ in eligibility, rounding, and retention.

Compatibility flags

This API has no model compatibility flags.