Frequently Asked Questions

J-ai Gateway is a unified API gateway that gives you access to multiple AI models — including large language models (GPT, Claude, Gemini, Llama), image generation (FLUX, Stable Diffusion), video generation, text-to-speech, and more — through a single, consistent API. Instead of managing separate integrations for each provider, you get one API key and one billing system for everything.

J-ai Gateway is built for developers, startups, and businesses in Africa and beyond who want to integrate AI capabilities into their products without managing multiple provider accounts and billing systems. Whether you're building a chatbot, generating images, or creating video content — one API covers it all.

Not necessarily. While the API is designed for developers, our web interface lets you chat with AI models, generate images, create videos, and use other AI tools directly from your browser — no coding required. The API is there when you're ready to build programmatically.

J-ai Gateway uses a pay-as-you-go credit system. You fund your wallet with Naira (₦), and credits are deducted per API call or job. Different models and features have different costs. There are no monthly subscriptions — you only pay for what you use.

We accept payments via bank transfer, card payments, and other methods supported by our payment processor (Monnify/Paystack). All transactions are processed in Nigerian Naira (₦).

Yes. For media generation and tool jobs, credits are deducted upfront to prevent abuse. If a job fails due to a provider error or system issue, credits are automatically refunded to your wallet. For chat completions, you are only charged for successful responses.

Credits do not expire as long as your account remains active. If your account is terminated for violation of our Terms of Service, unused credits may be forfeited.

1. Create a free account at aiplatform.dev/signup
2. Fund your wallet with a small amount to get started.
3. Go to API Keys in your dashboard and create a key.
4. Follow the API Documentation to make your first request.

We aggregate access to leading AI models across categories:
Chat: GPT-4o, GPT-4, Claude 3.5, Gemini Pro, Llama 3, Mistral, and more.
Image: FLUX, Stable Diffusion, DALL·E.
Video: Veo, Kling, and other video generation models.
Audio: KokoroTTS, ElevenLabs, and music generation models.

We regularly add new models. Check our Models page for the full list.

Rate limits control how many API requests you can make per minute per API key. Limits are configurable per key in your dashboard. If you exceed your limit, you'll receive an HTTP 429 (Too Many Requests) response. You can create additional API keys to spread load across projects.

Yes. Our chat completions endpoint supports streaming responses. Set "stream": true in your request to receive responses token-by-token via Server-Sent Events (SSE).

We take security seriously. API keys are hashed, connections use TLS encryption, and we follow industry best practices. Your inputs are transmitted to the AI model provider you select — we do not store your API payloads beyond what's needed for billing and debugging. See our Privacy Policy for full details.

Yes. You can create multiple API keys, each with its own name, rate limit, and usage tracking. This is useful for separating usage across projects, environments (dev/staging/production), or team members.

Teams let you collaborate with others under a shared wallet. The team admin creates the team, invites members, and sets credit limits per member. All usage is billed from the team admin's wallet. Members can create their own API keys within their allocated limits.

Each user gets a unique referral code (format: LITE-XXXXXX). When someone signs up using your code, both you and the referred user receive bonus credits. Share your referral link from the Referrals page.

Yes. The Usage page provides detailed analytics including total API calls, credits spent, per-key breakdowns, and job history. You can filter by date range and view performance by model.

A 402 (Payment Required) error means your wallet has insufficient credits to complete the request. Top up your wallet from the Wallet page and try again.

A 429 (Too Many Requests) means you've exceeded your API key's rate limit. Wait for the retry-after period indicated in the response headers, or create an additional API key to distribute your load. You can also increase your rate limit in the API Keys settings.

No. If a job fails due to a provider error, system issue, or any other reason on our end, credits are automatically refunded to your wallet. You will only be charged for successfully completed jobs.

Email us at support@jaiplatform.com and we'll get back to you as soon as possible. For urgent issues, include your account username and a description of the problem.

Yes. Contact us at support@jaiplatform.com to request account deletion. Your remaining balance (if any) will be refunded. We'll process your request and delete your personal data in accordance with our Privacy Policy.