Nova Premier

Amazon BedrockMCP Tool Call
amazon/nova-premierClosed API

Multimodal model for complex analysis, long-context understanding, tool use, and model distillation

Benchmark Pricing$2.50 / 1M in$12.50 / 1M out$0.63 cache read
Context: 1,000,000 tokens•Max Output: 10,000 tokens•Knowledge: 2024-10•Released: 2025-04-30

TECHNICAL SPECIFICATIONS

Context Window1,000,0001M tokens
Max Output10,00010K tokens
LicenseProprietaryCloud API only
Input Modalities
TextVisionPDFVideo
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Nova Premier natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 1,000,000 tokens, this model can handle extremely large MCP resource manifests, complete database schemas, and multiple active server tool definitions simultaneously without degradation.

API CALL INVOCATION EXAMPLE

// Example: Calling Nova Premier via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.AMAZON_API_KEY,
});

const response = await client.chat.completions.create({
  model: "amazon/nova-premier",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);

PRICING BY PROVIDER

3 providers
Amazon Bedrockus.amazon.nova-premier-v1:0
$2.50 / $12.50$0.63 cache
Kilo Gatewayamazon/nova-premier-v1
$2.50 / $12.50$0.63 cache
OpenRouteramazon/nova-premier-v1
$2.50 / $12.50$0.63 cache

Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.

Prompt Caching Active

This model supports prompt caching at $0.63 / 1M tokens, saving up to 75% on repetitive MCP tool definitions and system instructions.