Frequently Asked Questions
Everything You Need to Know About UMVA AI
Find answers to common questions about UMVA AI — our pricing, platform, API, IDE, security, billing, and more. If you cannot find what you are looking for, feel free to reach out to our support team.
General
What is UMVA AI?
UMVA AI is a pay-as-you-go AI platform that provides the cheapest AI inference for coding and general use. It includes an AI-powered IDE that runs on macOS, Windows, and Linux, along with API access for integrating AI into your own tools and workflows. All text models feature a 1M context window, and you only pay for what you use — no subscriptions, no monthly commitments.
Is UMVA AI free to use?
UMVA AI is pay-as-you-go from the start — no free trial needed because you only pay for what you use. Just add as little as $0.10 to your wallet and start coding immediately. No credit card is required to create an account, and you can begin with the minimum deposit to test the service before adding more funds.
Do I need to create an account?
Yes, you need to create a free UMVA account to use our AI services. Registration requires only an email address and password. No KYC or identity verification is required. You can add funds and start using AI immediately after registration.
Pricing & Billing
How does pay-as-you-go pricing work?
You add funds to your UMVA wallet and pay per token as you use AI models. Pricing is based on input and output tokens per million tokens — starting from as low as $0.10. Your usage is deducted from your balance in real time. There are no monthly fees, no subscription tiers, and no expiration on your credits. Use as much or as little as you want, whenever you want.
What are the current model prices?
Our pricing starts at $0.10 per million input tokens for umva-code-fast. umva-code-agent and umva-code-pro are priced at $0.50/M input tokens, and umva-code-architect at $0.90/M input tokens. Output tokens are priced at $0.30/M for fast models and $0.90-$1.80/M for premium models. All prices are in USD and you only pay for actual usage.
Do my credits expire?
No. Funds in your UMVA wallet never expire. You can keep your balance for as long as you like and use it whenever you need. There are no inactivity fees or expiration dates.
Technical
What models does UMVA AI offer?
UMVA AI offers four specialized models: umva-code-fast (fast and lightweight for quick edits), umva-code-agent (fast with extended thinking for complex reasoning), umva-code-pro (advanced model for complex tasks), and umva-code-architect (pro with extended thinking for architecture and large-scale refactoring). All models feature a 1 million token context window, tool use support, and text-only processing.
What is the context window size?
All UMVA AI text models feature a 1 million token (1M) context window. This allows you to process extremely long documents, entire codebases, lengthy conversations, or large datasets in a single prompt without needing to chunk or truncate content. This is one of the largest context windows available from any AI provider.
Is the API OpenAI-compatible?
Yes. UMVA AI provides a fully OpenAI-compatible API. Any client library, tool, or application that works with OpenAI's API will work with UMVA AI by simply changing the base URL and API key. This includes the OpenAI Python/Node.js SDKs, LangChain, LlamaIndex, and more.
IDE & Integrations
What is the UMVA AI IDE?
The UMVA AI IDE is a free, native AI-powered code editor that runs on macOS, Windows, and Linux. It includes built-in AI chat, inline code completion, git integration, a full terminal, and syntax highlighting for hundreds of languages. The IDE is pre-configured with UMVA AI, so you can start coding with AI immediately after logging in.
Can I use UMVA AI with VS Code?
Yes. UMVA AI works with VS Code through the Continue.dev extension. Simply install the extension, configure it with your UMVA API key and endpoint, and start using UMVA AI models for code completion, chat, and refactoring within VS Code.
Does UMVA AI work with JetBrains IDEs?
Yes. UMVA AI integrates with all JetBrains IDEs (IntelliJ IDEA, PyCharm, WebStorm, GoLand, etc.) through the Continue.dev plugin or by configuring the built-in AI Assistant feature with UMVA AI as a custom provider.
Security & Privacy
Do you train on my data?
No. We never use your prompts, code, or conversations to train or improve our AI models. Your data is processed solely to fulfill your request and is immediately discarded. No training runs, no model fine-tuning, no data harvesting. Period.
Do you store my prompts?
No. We do not store your prompts or generated responses on our servers. Once the response is delivered to you, the data is gone. We do not log, archive, or review your conversations. Aggregated usage metrics (token counts, model used, timestamps) are collected for billing and operations only.
How are my API keys protected?
API keys are hashed using bcrypt and never stored in plaintext. All communication between your IDE or API client and our servers is encrypted using TLS 1.3. You can generate, rotate, and revoke API keys from your dashboard at any time.
Payments
What payment methods do you accept?
We accept Visa, Mastercard, American Express, and Verve cards, as well as cryptocurrency payments including USDT (TRC20 & BEP20), USDC, Bitcoin, and Ethereum. All prices are in USD, and you can top up your account with any of these payment methods. No KYC required for crypto payments.
What is the minimum deposit?
The minimum deposit is $1.00 for card and crypto payments. For bank transfers, the minimum is $10.00. There is no maximum deposit limit. You can add any amount above the minimum to your wallet at any time.
Can I get a refund?
Wallet top-ups are non-refundable, but unused funds remain in your wallet indefinitely with no expiration. Since you only pay for what you use, there are no surprise charges. If you have a specific issue, please contact our support team and we will review it on a case-by-case basis.
Still Have Questions?
Our support team is here to help. Reach out anytime and we will get back to you promptly.