---
last_updated: 2026-11-21
source_url: https://opper.ai/amazon/nova-micro
title: "Amazon Nova Micro by Amazon"
description: "Amazon Nova Micro, a fast text-only model for real-time summarization, translation, classification and simple reasoning."
---

# Amazon Nova Micro

By [Amazon](https://opper.ai/amazon).

Released 3 Dec 2024 · [Announcement](https://aws.amazon.com/blogs/aws/introducing-amazon-nova-frontier-intelligence-and-industry-leading-price-performance/) · [All Amazon releases](https://opper.ai/model-releases/amazon)

Nova Micro is Amazon's fastest and most efficient text-only model, optimized for speed and cost in real-time applications. With a 128K token context window and very low latency, it excels at text summarization, content classification, translation, and interactive chat where responsiveness matters.

Designed as the entry-level member of the Nova family, Micro handles text-in, text-out tasks including simple mathematical reasoning, basic coding, interactive brainstorming, and automated FAQ generation. While it lacks vision and video capabilities, its speed and cost efficiency make it well suited to customer-facing chat, content processing pipelines, and quick analytical tasks.

Nova Micro supports prompt caching, function calling for tool use, and customization through fine-tuning or model distillation to improve accuracy on domain-specific tasks. The model understands and generates text in over 200 languages, with particularly strong performance in major languages.

Launched in December 2024, Nova Micro serves developers who need immediate inference speed without vision requirements, making it suitable for latency-sensitive applications.

## Available routes

Amazon Nova Micro runs on 1 route through the Opper gateway. Prices are per 1M tokens. In the EU it is served by AWS Bedrock. [See every model hosted in the EU](https://opper.ai/models/eu). Its routes and prices, live from the catalogue, are public JSON with no API key needed at https://api.opper.ai/v3/models?q=aws%2Fnova-micro-eu.

| Provider | Model id | Region | Zero data retention | Training | Input | Output | Cache read |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [AWS Bedrock](https://opper.ai/provider/aws-bedrock) | `aws/nova-micro-eu` | EU | Yes | No | $0.04 | $0.14 | Input price |

## Key info

- Model id: `aws/nova-micro-eu`
- Input: Text
- Output: Text
- Features: Tools, Structured output
- Context window: 128K
- Max output: 5K
- Input price: $0.04 per 1M tokens
- Output price: $0.14 per 1M tokens
- Released: 3 Dec 2024
- EU residency available
- Zero data retention on pay-as-you-go
- No training by default

## Data handling per route

Each route hosting Amazon Nova Micro has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

### AWS Bedrock — EU

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU.

- Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
- Training: No training on customer data.
- Logging: None
- Abuse monitoring: Always on, keeps nothing
- Subprocessor access: No subprocessor reads content
- Transfer mechanism: Not applicable — data stays in EU

Verified by Opper on 2026-10-14.

## Benchmarks

Independent benchmark scores via [Artificial Analysis](https://artificialanalysis.ai) ([view on AA](https://artificialanalysis.ai/models/nova-micro)). Indices and domain scores are out of 100, Omniscience runs from −100 to 100, Briefcase is an Elo rating, and the other evaluation scores are the share of tasks solved.

- Global rank: #432 of 520 LLMs on the [LLM leaderboard](https://opper.ai/llm-leaderboard)
- Tier: Efficient
- Output speed: 278 tok/s
- Intelligence Index (previous version): 5.9

### Coding

- LiveCodeBench: 14%

### Agentic & knowledge work

- Terminal-Bench Hard: 2%
- τ²-Bench Telecom: 14%

### Science & reasoning

- Humanity's Last Exam: 5%
- GPQA Diamond: 36%
- Long-context reasoning: 13%

### Knowledge

- MMLU-Pro: 53%

### Math & instruction following

- AIME 2025: 6%
- IFBench: 29%

## Get started

Call Amazon Nova Micro through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Amazon Nova Micro is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

### Set it up with your agent

Paste this into a coding agent like Claude Code, Cursor or Codex and it will wire up Opper for you:

```text
Use curl to download, read and follow: https://skills.opper.ai Call Amazon Nova Micro
```

### Or call it directly

OpenAI:

```javascript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const completion = await client.chat.completions.create({
  model: "aws/nova-micro-eu",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);
```

Anthropic:

```javascript
import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const message = await client.messages.create({
  model: "aws/nova-micro-eu",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello" }],
});
console.log(message.content);
```

Gemini:

```javascript
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  apiKey: process.env.OPPER_API_KEY,
  httpOptions: { baseUrl: "https://api.opper.ai/v3/compat" },
});

const response = await ai.models.generateContent({
  model: "aws/nova-micro-eu",
  contents: "Hello",
});
console.log(response.text);
```

cURL:

```bash
curl https://api.opper.ai/v3/compat/chat/completions \
  -H "Authorization: Bearer $OPPER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "aws/nova-micro-eu",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'
```

## Use Amazon Nova Micro in your apps

Pick your tool to see how to run it on Amazon Nova Micro through Opper.

- [Claude Code](https://opper.ai/apps/claude-code/nova-micro)
- [Claude Cowork](https://opper.ai/apps/claude-cowork/nova-micro)
- [Codex](https://opper.ai/apps/codex/nova-micro)
- [DeepSeek Harness](https://opper.ai/apps/deepseek-harness/nova-micro)
- [GitHub Copilot CLI](https://opper.ai/apps/github-copilot-cli/nova-micro)
- [Aider](https://opper.ai/apps/aider/nova-micro)
- [Goose](https://opper.ai/apps/goose/nova-micro)
- [Droid](https://opper.ai/apps/droid/nova-micro)
- [OpenCode](https://opper.ai/apps/opencode/nova-micro)
- [Pi](https://opper.ai/apps/pi/nova-micro)
- [OpenClaw](https://opper.ai/apps/openclaw/nova-micro)
- [Hermes](https://opper.ai/apps/hermes/nova-micro)
- [Copilot for Obsidian](https://opper.ai/apps/obsidian-copilot/nova-micro)
- [OmniRoute](https://opper.ai/apps/omniroute/nova-micro)
- [Cursor](https://opper.ai/apps/cursor/nova-micro)
- [Cline](https://opper.ai/apps/cline/nova-micro)
- [Continue](https://opper.ai/apps/continue/nova-micro)
- [Kilo Code](https://opper.ai/apps/kilo-code/nova-micro)
- [GitHub Copilot](https://opper.ai/apps/github-copilot/nova-micro)
- [Zed](https://opper.ai/apps/zed/nova-micro)
- [JetBrains AI Assistant](https://opper.ai/apps/jetbrains-ai-assistant/nova-micro)
- [Voidleap Code](https://opper.ai/apps/voidleap-code/nova-micro)
- [n8n](https://opper.ai/apps/n8n/nova-micro)
- [LibreChat](https://opper.ai/apps/librechat/nova-micro)
- [Open WebUI](https://opper.ai/apps/open-webui/nova-micro)
- [See all apps](https://opper.ai/apps)

## Other models from Amazon

- [Amazon Nova Pro](https://opper.ai/amazon/nova-pro)
- [Amazon Nova Lite](https://opper.ai/amazon/nova-lite)
- [Amazon Nova 2 Lite](https://opper.ai/amazon/nova-2-lite)
