TypingMind×
AWS BedrockHow to use Nova 2 Lite with your AWS Bedrock API key on TypingMind
Learn how to access and use Nova 2 Lite with your AWS Bedrock API key through TypingMind. Get started with this AI model in minutes.
Multimodal reasoning model for visual analysis, planning, and tool use
AWS Bedrock is a fully managed AWS service that gives you access to 100+ foundation models from leading AI providers, including Anthropic Claude, Meta Llama, Mistral, and more, through a single OpenAI-compatible API.
Bedrock uses pay-as-you-go pricing with no monthly fees or minimum commitments, and requests run inside your own AWS account. Long-term API keys work with any OpenAI-compatible client, and you can monitor usage in the AWS console.
See the official AWS Bedrock documentation for more details.
Nova 2 Lite Overview
| Model Name | Nova 2 Lite |
| Provider | AWS Bedrock |
| Model ID | amazon.nova-2-lite-v1:0 |
| Model Logo | Get the logo URL |
| Release Date | Dec 2, 2025 |
| Last Updated | Dec 1, 2025 |
| Knowledge Cutoff | 2025-10 |
| Context Window | 1,000,000 tokens |
| Max Output | 65,535 tokens |
| Pricing /1M tokens | $0.33 input $2.75 output $0.0825 cache read |
| Input Modalities | text, image, video, pdf |
| Output Modalities | text |
| Capabilities | File UploadReasoningTool CallingTemperature Control |
Complete Setup Guide
Get Your AWS Bedrock API Key
First, you'll need to obtain an API key from AWS Bedrock. This key allows you to access their AI models directly and pay only for what you use.
-
Go to aws.amazon.com and create an AWS account if you don't have one. Amazon Bedrock gives you access to serverless foundation models in your AWS Region without enabling each model manually.
-
Open the AWS Bedrock console and go to API keys.
-
Click Generate API key and choose a long-term key. Long-term keys are valid from 1 day up to 365 days (or never expire) and are linked to an IAM user. Short-term keys expire after 12 hours and use AWS Signature V4, so they don't suit a chat app.
-
Set an expiration, then copy and save the key. You won't be able to see it again.
Sometimes, this provider will require you to add a payment method to your account before you can use your API key to chat with AI. So, to avoid any hiccups, make sure you've got a payment method set up and ready to go!
Important: Keep your API key secure and never share it publicly. Store it safely as you'll need it to connect with TypingMind.
Configure TypingMind with AWS Bedrock API Key
Open the Models page
Open TypingMind, click "Models" in the left sidebar, then click "Add custom model" in the top right corner.
Enter the model details
Keep "Create Manually" selected and fill in the model details:
Name:Nova 2 Lite via AWS Bedrock(or your preferred name)Model ID:amazon.nova-2-lite-v1:0for example (check AWS Bedrock model list)Context Length: Enter the model's context window (e.g., 1000000 for amazon.nova-2-lite-v1:0)
Set up authentication
In the "Authentication" tab, set the connection details:
API Type:OpenAI Chat Completions APIEndpoint URL:https://bedrock-mantle.<AWS_REGION>.api.aws/v1/chat/completionsExample:
https://bedrock-mantle.us-east-1.api.aws/v1/chat/completionsAuthentication Type:API Key via HTTP HeaderHeader Key:AuthorizationHeader Value:Bearer <AWS_BEDROCK_API_KEY>
Add pricing (optional)
Open the "Pricing" tab and enter the model's input, output, and cache prices per 1M tokens so TypingMind can estimate your usage costs.
Check the capabilities
In the "Capabilities" tab, keep "Auto check capabilities on save" on so TypingMind detects supported features like plugins, image input, and thinking, or enable them manually.
Test and save
Click "Test & Save" to verify the connection and add the model.
Start chatting with Nova 2 Lite
Now you can start chatting with Nova 2 Lite through TypingMind:
- Select Nova 2 Lite from the model dropdown menu
- Start typing your message in the chat input
- Enjoy faster responses and better features than the official interface
- Switch between different AI models as needed
💡 Pro tips for better results:
- Use specific, detailed prompts for better responses (How to use Prompt Library)
- Create AI agents with custom instructions for repeated tasks (How to create AI Agents)
- Use plugins to extend Nova 2 Lite with web search, code execution, and more (How to use plugins)
- Upload documents and images directly to chat for AI analysis and discussion (Chat with documents)
Why TypingMind + AWS Bedrock?
Chat with Nova 2 Lite and 200+ other models in one workspace, using your own AWS Bedrock API key.
Best-in-class UI
TypingMind's interface is far superior to standard chat UIs.
Model flexibility
Switch between Nova 2 Lite and 200+ models instantly.
Cost control
Pay only for what you use through AWS Bedrock.
One-time purchase
Buy TypingMind once, use forever with any AWS Bedrock model.
Data privacy
Your conversations are stored locally by default, not on external servers.
Plugins, MCP, Skills & AI agents
Extend Nova 2 Lite with web search, image generation, and custom AI agents.
Frequently Asked Questions
Do I need a subscription to use Nova 2 Lite?
No. With your own AWS Bedrock API key, you pay only for what you use, with no monthly subscription. TypingMind is also a one-time purchase, not a subscription.
How much does it cost to use Nova 2 Lite?
Nova 2 Lite costs $0.33/1M input tokens and $2.75/1M output tokens via AWS Bedrock. A typical conversation costs around $0.01-0.10, depending on length.
Can I use other models besides Nova 2 Lite?
Yes. Any model your AWS Bedrock API key can access works in TypingMind, and you can switch between it and models from other providers in the same chat.
Is my data private when using Nova 2 Lite with TypingMind?
TypingMind stores your conversations locally (in your browser on the web version, on your device in the desktop app). Your messages are sent to AWS Bedrock with your API key, so check AWS Bedrock's data policy for how it handles API requests.
Which AWS regions support AWS Bedrock?
AWS Bedrock is available in multiple regions including us-east-1 (N. Virginia), us-west-2 (Oregon), eu-west-1 (Ireland), ap-southeast-1 (Singapore), and more. Model availability varies by region, so check the AWS Bedrock documentation and use your region in the endpoint URL.
