Appearance
AI Configuration β
Quizora's AI writes quiz questions, quiz descriptions, SEO text, and personalised result feedback. You choose where that AI comes from. OpenAI is one option, not a requirement:
- Cloud AI with an API key: OpenAI, Anthropic Claude, Google Gemini, Groq, OpenRouter, DeepSeek, Mistral, or Azure OpenAI
- Self-hosted and free: run open models (Llama, Qwen, Mistral, Gemmaβ¦) on your own server with Ollama or LM Studio. No API key, no per-request cost
- Any OpenAI-compatible API: Together, Fireworks, xAI, Perplexity, vLLM, LocalAIβ¦
- Offline: no AI at all. Creators paste study notes and Quizora builds questions from them
Everything is set in Admin β Settings β AI. There's nothing to configure in .env.
New in v1.5.1
Before 1.5.1, Quizora only worked with OpenAI. Now it works with all the providers above, and the Test connection button checks a provider before you save it.
Choosing a provider β
| Provider | Cost | API key | Good for |
|---|---|---|---|
| OpenAI | Pay per use | platform.openai.com | Best all-round quality (gpt-4o) |
| Anthropic Claude | Pay per use | console.anthropic.com | Careful, well-written questions and explanations |
| Google Gemini | Free tier, then pay per use | aistudio.google.com | Low cost, generous free tier |
| Groq | Free tier (rate-limited) | console.groq.com | Very fast open models |
| OpenRouter | Pay per use, some free models | openrouter.ai | One key for hundreds of models |
| DeepSeek | Very low cost | platform.deepseek.com | Cheapest paid option |
| Mistral AI | Pay per use, free tier | console.mistral.ai | EU-hosted |
| Azure OpenAI | Your Azure contract | Azure portal | Companies already on Azure |
| Ollama | Free (your server) | None | Privacy, no ongoing cost |
| LM Studio | Free (your machine) | None | Trying local models from a desktop app |
| Custom OpenAI-compatible | Depends | Depends | Anything else that speaks the OpenAI API |
| Offline | Free | None | No AI at all; questions come from pasted text |
Which one should I pick?
- Best quality: OpenAI
gpt-4oor Claudeclaude-sonnet-5-5. - Lowest cost: Gemini
gemini-2.5-flash(free tier) or DeepSeekdeepseek-chat. - Zero cost and private: Ollama with
llama3.1(8B) or, if your server has the memory,qwen2.5:14b. - No AI at all: Offline.
Setting up a cloud provider β
- Create an account with the provider and copy an API key (links in the table above).
- Go to Admin β Settings β AI and pick the provider.
- Paste the key into API Key. The Model field fills in a suggested model; change it to any model the provider offers.
- Click Test connection. A green "Connected to β¦" message means it works.
- Click Save Settings.
The Base URL is pre-filled for every preset. Change it only if the provider gives you a different endpoint.
One key at a time
Quizora stores one API key. When you switch provider, paste that provider's key; the saved key is only ever sent to the selected provider. Self-hosted providers (Ollama, LM Studio) never receive it.
Azure OpenAI β
Pick Azure OpenAI, then enter:
- Base URL:
https://YOUR-RESOURCE.openai.azure.com/openai/v1 - API Key: the key from your Azure OpenAI resource
- Deployment name: the name you gave your model deployment (e.g.
gpt-4o)
Custom OpenAI-compatible API β
Pick Custom OpenAI-compatible API and enter the provider's endpoint (usually ending in /v1), its key and a model name. Examples:
| Service | Base URL |
|---|---|
| Together AI | https://api.together.xyz/v1 |
| Fireworks | https://api.fireworks.ai/inference/v1 |
| xAI (Grok) | https://api.x.ai/v1 |
| Perplexity | https://api.perplexity.ai |
| vLLM / LocalAI | http://your-server:8000/v1 |
Free, self-hosted AI with Ollama β
Ollama runs open models on your own server. There's no API key and no per-request bill.
1. Install Ollama on the Quizora server (or any machine Quizora can reach):
bash
curl -fsSL https://ollama.com/install.sh | sh2. Download a model:
bash
ollama pull llama3.13. In Quizora, pick Ollama in Admin β Settings β AI. Leave Base URL blank if Ollama runs on the same server (http://localhost:11434/v1), or enter its address, e.g. http://192.168.1.20:11434/v1. Click Test connection, then Save Settings.
| Model | RAM needed | Notes |
|---|---|---|
llama3.2 (3B) | ~4 GB | Fastest; fine for short quizzes |
llama3.1 (8B) | ~8 GB | Recommended starting point |
qwen2.5:14b | ~16 GB | Noticeably better questions |
qwen2.5:32b | ~32 GB | Close to cloud quality |
Speed
On a CPU-only server, a 10-question quiz with an 8B model can take a minute or more. Raise Request timeout (default 120 s) if generations time out, ask for fewer questions at a time, or use a server with a GPU.
Ollama in Docker
If Quizora runs in Docker and Ollama on the host, use http://host.docker.internal:11434/v1 as the Base URL. To reach Ollama from another machine, start it with OLLAMA_HOST=0.0.0.0 ollama serve.
LM Studio β
Install LM Studio, download a model, and start its local server (default port 1234). In Quizora pick LM Studio, enter the model identifier shown in LM Studio's server tab (e.g. qwen2.5-7b-instruct), and test the connection.
Offline mode (no AI) β
Pick Offline and Quizora makes no AI calls at all: no key, no network, no cost.
Instead of a topic, creators paste study material: lecture notes, a textbook passage, an article. Quizora turns its sentences into questions:
| Type | Example from "The Calvin cycle uses carbon dioxide to build glucose." |
|---|---|
| Fill in the blank | The ______ cycle uses carbon dioxide to build glucose. β Calvin |
| Multiple choice | Same sentence, with key terms from elsewhere in the text as wrong options |
| True / False | The original sentence (True), or with one key term swapped (False) |
Each usable sentence gives one question, so paste at least a few paragraphs. Up to 20,000 characters fit in the box. Quiz descriptions, SEO text and result feedback use built-in templates in this mode.
INFO
Offline mode can't invent facts, so it only asks about what's in the pasted text. Review the questions before publishing, as you would with any generated content.
What the AI is used for β
| Feature | Where | Offline mode |
|---|---|---|
| Generate questions | Creator β AI Generator, and the AI panel in the quiz wizard | Built from pasted text |
| Quiz description | Creator β Quizzes β Basic Info β Generate with AI | Template |
| SEO description and keywords | Creator β Quizzes β SEO | Template |
| Student result feedback | Result page (when the quiz has AI feedback on) | Score-based summary |
| Creator quiz insight | Creator β Reports β Generate AI insight | Flags questions most learners miss |
| Cover image | Creator β Quizzes β Basic Info | Always drawn locally; no AI needed |
Credit system β
Quizora includes a built-in AI credit system so you can control how much free generation each creator gets, and charge for generations beyond the free quota. It works the same with every provider, including Offline.
| Situation | What happens |
|---|---|
| Creator has free credits remaining | Generation is free β no charge |
| Free credits exhausted | Deducted from creator's wallet balance |
| Wallet is empty | Generation is blocked until the creator tops up |
| The AI reply can't be turned into questions | The credit is refunded automatically |
| Setting | Description | Default |
|---|---|---|
| Free Generations per New User | How many AI prompts each new creator gets for free | 10 |
| Charge per Generation | Amount deducted per prompt beyond the free quota | βΉ5.00 |
These defaults apply to all creators. You can override them per subscription plan. For a free provider such as Ollama, you can set the charge to 0, or keep it as a revenue stream.
Per-plan AI quotas β
When you create or edit a subscription plan (Admin β Plans), you can set:
- AI Free Generations β monthly free quota for this plan tier
- AI Charge per Generation β custom per-prompt rate for this plan tier
Monitoring AI usage β
Go to Admin β AI Generation Logs to see:
- Which creators are generating the most
- Which provider and model handled each request (e.g.
gpt-4o,ollama:llama3.1,offline) - Token usage per generation
- Success/failure status and error messages
Troubleshooting β
| Problem | Fix |
|---|---|
| Test connection: "Failed to connect" | The Base URL is wrong or the server can't reach the provider. For Ollama, check it's running (ollama list) and reachable from the Quizora server. |
| 401 / "invalid API key" | The key belongs to a different provider, or has been revoked. Paste a fresh key for the selected provider. |
| 404 / "model not found" | The model name doesn't exist on that provider. Pick a suggestion from the Model field, or for Ollama run ollama pull <model>. |
| Generation times out | Raise Request timeout, ask for fewer questions, or use a faster model. Also check your web server's own timeout (e.g. proxy_read_timeout in Nginx). |
| "The AI reply could not be turned into questions" | Smaller models sometimes ignore the format. Try again, ask for fewer questions, or use a larger model. The credit is refunded. |