Support
Frequently Asked Questions
Find answers to common questions or search for specific topics
How does this work?
Using NanoGPT requires funds in your account. Add funds by going to your balance and depositing via credit card or using crypto.
To chat with ChatGPT, Claude or other models click Chat and type in the textbox at the bottom of the page. Our default model is ChatGPT-4o, you can change this at any time.
To generate an image or images, click New Image and type your prompt in the textbox. Our default model is Flux Schnell which gives 10 free generations per day currently, both the model and resolution can be changed.
Are you affiliated with Karpathy's NanoGPT?
No. We are not affiliated with Andrej Karpathy or his nanoGPT project. This NanoGPT service is an independent product.
Karpathy's nanoGPT is an open-source educational project that explores how to build and train your own GPT-style LLM (AI model).
How do I start a new conversation?
Click Chat and a new chat will be opened. Every chat is completely separate, no data or information is shared between chats.
Can I create an account?
Yes, you can create an account by clicking sign in on the bottom of the menu. Creating an account allows us to securely store your balance on our servers, providing a seamless experience across devices. However, this is optional, and you can still use NanoGPT without an account with everything stored locally on your device. Conversations are always stored only locally, not on our servers.
Do you have an app?
Yes, you can install us as a Progressive Web App and we have a Chrome Extension that allows you to query NanoGPT anytime during your browsing.
What is a model?
As explained by ChatGPT itself, "a model is a type of AI that's trained to understand, interpret, generate, and respond to human language. It learns from a vast dataset of text and develops an understanding of language patterns, grammar, facts, and even nuances like humor or sarcasm."
We would describe these models as fantastic assistants on a wide range of topics: personal advice, programming, helping with learning, writing, medical questions and being an intelligent partner in practically any subject you can think of.
What are the differences between models?
Some of the models we offer are open-source, some are closed-source. The famous ones such as ChatGPT and Claude are closed-source and are seen as the most advanced models.
Open-source models such as LLama and DeepSeek are generally cheaper, but do less well on most benchmarks.
Most models have different gradations. GPT-4 is "smarter" than GPT-3, while Claude 4 is smarter than Claude 3. Prices tend to reflect this.
How do you rank models?
We use independent leaderboards to rank text, image and video models, the top model in the list being the current best. For text, we use LMArena's leaderboard. For images, we use Artificial Analysis Image Leaderboard. For video, we use Artificial Analysis Video Leaderboard.
What happens when I switch model within a chat?
Any text that is in the conversation so far gets sent to the model that you are using, every time. When you start a new conversation nothing except your new message gets sent. When you have a conversation where a few messages have gone back and forth, it means the previous messages are also sent to the model.
It does not matter for this whether you keep using the same model or switch halfway through. Switching between models halfway through the chat means model B gets sent your prompt along with the message history in that conversation so far with model A, and uses it all to generate a reply.
Do you offer prompt caching?
Yes, we offer prompt caching for Claude models. Enable it in settings by clicking "Adjust Settings" or the gear icon.
Prompt caching stores frequently used content (system prompts, conversation history) in memory, providing faster responses and up to 90% cost savings on subsequent requests. It's ideal for document analysis, RAG applications, and long conversations where you repeatedly reference the same content.
Claude's strength at analyzing long documents makes prompt caching particularly valuable for research and knowledge work involving existing documents or structured data.
What is "Vision"?
Vision means a model can "see" images — it accepts pictures or screenshots as input alongside text and analyzes them to answer questions, describe content, read text (OCR), or reason about what's shown.
How can I adjust settings for image and video models?
For both video and image models, you can adjust various settings by clicking the "Adjust Settings" button (gear icon on mobile) when you're in image or video generation mode. This allows you to customize parameters like resolution, aspect ratio, and other model-specific options to better suit your needs.
Alternatively, visit our Media Generation page which is better suited to image and video generation.
Can I generate an image based on another image?
We have models that support this - they are listed with IMG2IMG behind their name when you go to select your image model of choice!
What can I do with the images I generate?
Anything you generate is completely yours to do with as you wish. Use, sell, reprint, merchandise, they are your property.
What video models are supported?
We currently support multiple video providers like Google Veo, Tencent Hunyuan, and Kling via FAL/Runware.
How do I generate videos?
To generate videos, select a video model from the model dropdown when creating content. You can choose from various video generation models that are ranked based on quality and performance. Simply enter your prompt describing the video you want to create, and the AI will generate it for you.
Alternatively, visit our Media Generation page which is better suited to image and video generation.
What video formats and lengths are supported?
The supported video formats and lengths depend on the specific video model you choose. Different models may offer various resolution options, durations, and output formats. You can adjust these settings using the "Adjust Settings" button when in video generation mode.
Alternatively, visit our Media Generation page which is better suited to image and video generation.
Can I create videos from images?
Some of our video models support image-to-video generation, allowing you to animate existing images or use them as starting points for video creation. Look for models that specifically mention image-to-video (IMG2VID) capabilities when selecting your video model.
How do I go back to old conversations?
All conversations are stored locally on your device and can be accessed by going to the Conversations tab. Any conversation can be continued at any time. Note that you can only access conversations on the same device where you originally had them, as they are stored locally in your browser.
How can I save my conversation?
Conversations are automatically saved locally on your device and can be accessed by going to the Conversations tab. You can also download your conversations from the conversations tab to keep a backup or transfer them to another device, and you can similarly download a conversation by exporting it using the three dots at the top right of your conversation.
How can I backup my data without an account?
If you're using NanoGPT without creating an account, you can still backup your important data:
For your funds: Go to Settings to find your UUID (unique identifier). You can use this UUID to restore your balance if you ever lose access to your device or clear your browser data.
For your conversations: Export your chats from the Conversations page and save them locally. You can later import these conversations back into NanoGPT from the same page. Note that conversations are stored in your browser's localStorage (accessible via F12 → Application → IndexedDB → database → conversations). We do not store conversations.
What do you do with my data?
We strongly value privacy. You are not required to create an account or provide any personal information to use this website.
By default we do not store anything except a cookie containing your account number with your associated balance. Chats you have via this website are stored locally in your browser. When you clear your website data, we cannot help you retrieve your conversations or images. We do not store them, we do not keep them as a backup.
When we communicate with model providers we send your prompt and the prompts you've sent previously in that conversation. No conversation is linked to any other conversation, and no identifiable information is sent along with the prompts. From the provider's perspective each conversation is a standalone conversation that is only identifiable by our API key, which is the same for all users and all conversations.
Across all providers we use, we apply a minimum-retention and maximum-deletion posture by using the strictest retention and deletion settings they offer. Providers still run their own infrastructure and legal/compliance policies, so their provider-side terms ultimately govern what they retain.
For more information on how we deal with privacy see our Privacy page in which we explain it more thoroughly.
Is web search private? Who provides web search?
Our web search uses LinkUp by default. LinkUp is privacy-focused and operates with a no-log policy, meaning they don't store or track your search queries. You can switch to Tavily or Exa in Settings if you prefer a different provider.
Web search is a separate service from our AI models and operates independently from other privacy features like TEE (Trusted Execution Environments). Provider-specific privacy policies apply to the web search portion.
Does web search work with TEE models? Is it still private?
When you use web search with a TEE (Trusted Execution Environment) model, it's important to understand that these are two separate services with different privacy characteristics.
The TEE model itself maintains its encrypted, confidential computing environment for processing your prompts. However, the web search portion is handled by the provider you select in Settings (LinkUp by default, with Tavily and Exa available), which is separate from the TEE infrastructure.
Web search queries are not processed within the TEE environment. This means that when you combine TEE models with web search, the TEE encryption applies only to the AI model processing, not to the web search functionality.
How much balance gets added when I deposit crypto?
When you deposit crypto we credit you with a USD balance based on the current exchange rate to dollars (with no fee added). When you deposit Nano we add it to your account as a Nano balance, and you get a 5% discount on your usage.
What is a UUID?
You can use our service without creating an account. We generate a random session user ID (a "UUID") for every user. This UUID is stored in your browser and is what identifies your account balance. If you ever clear your browser data, you can use this UUID to restore your balance, so be sure to save it somewhere safe. It is practically impossible for someone to guess your UUID and claim your balance. The number of possible UUIDs is so large (over 5 undecillion) that it would be easier to win the lottery several times than to guess one. We also rate-limit attempts to prevent mass guessing.
Can I see some reviews?
Yes! You can check out our testimonials page which features reviews from our users with links to the original sources. We're transparent about user feedback and encourage you to verify the authenticity of reviews by checking the source links.
Do you offer volume discounts?
Yes! If you spend $500 or more on text models in a single day, you automatically qualify for a 10% discount on text models the following day. This discount is recalculated daily.
The discount applies to all text/chat models (like GPT-4, Claude, Gemini, etc.) and is applied automatically. You can see if you have this discount active in your Settings page under "Discounts".
Note: This discount does not stack with referral or subscription discounts, but does stack with the 5% Nano payment discount.
What are your rate limits?
Generally speaking if you are using one of the more well known models such as the ChatGPT, Claude, Gemini etc, you will not be rate limited unless you are doing thousands of requests per minute or more than a billion tokens per day. If this is your situation, reach out to us so we can make sure to provide proper service (and possibly a discount).
Do you support BYOK (Bring Your Own Key)?
We have this in closed beta. If you want to participate, reach out to us at support@nano-gpt.com and tell us which providers you would like to use this with.
I'm a provider, can I work with you?
We work together with many providers. If you think you offer models that we don't have yet, or can offer models for a lower price, feel free to reach out to us either at support@nano-gpt.com or find us on our Discord.
Is what you are doing legal?
Yes. We pay the different providers for the usage of their models - while some think that we take out one subscription to for example ChatGPT and share it between users, this is not the case. We pay for each request and each token processed via different APIs - more usage means more income for the providers.
Why did you create this service?
ChatGPT, Claude and other AI assistants assist many people with everything from everyday tasks to complex solutions. They have been proven to be incredibly helpful tools in furthering knowledge, teaching new skills, and broadening perspectives.
Not everyone has access to these models. With global median income at ~$250 per month, a $20 per month subscription is expensive. Billions of people are unable or unwilling to pay this much, limiting their ability to use state-of-the-art models.
Many people do not have access to a credit card. Some might live in countries where you don't want anyone to know what questions you are asking ChatGPT.
This service is for those people. Rather than paying upfront, people pay only for what they use. NanoGPT can be used anonymously, by anyone, from anywhere. We accept credit cards but also offer the option to add via crypto for those without credit card access.
ChatGPT, Claude and other models should be available to anyone in the world and we are trying to make that happen.
What is Nano?
Nano offers instant payments at zero fees. It's an environmentally friendly cryptocurrency focused on scaling payments. It's possible to try Nano for free by downloading a wallet like Nautilus (iOS, Android) and getting some free Nano from a Nanodrop faucet.
This Substack article provides further reading on Nano while the Nano Foundation website offers more content.
Why do you use Nano?
We use Nano because it offers instant transactions at zero fees to anyone in the world. It's very easy to develop on, with broad documentation and quick testing since all transactions are feeless and provide immediate feedback.
Nano's vision is to be a digital currency for everyone. We strongly believe in the vision of allowing anyone in the world to transact instantly without fees, without giving away personal details and without requiring anyone's permission.
We also see Nano as a store of value, and would rather hold a hard form of money with a fixed supply than a form of fiat money.
Are there other places I can use Nano?
Nano is a growing digital currency and is continuously being adopted by people and merchants around the world. For a list of businesses accepting Nano, see the Nano Hub.
Can't find what you're looking for?
Start a ticket above and we'll help you directly.