Plug any AI model into Odoo, with a hard monthly cap.
Connect Odoo to OpenAI, Claude, Gemini, Grok, Azure OpenAI and four more providers from one screen. Set a monthly token cap per provider and see every call in a usage log.
AI Base is the connection layer between Odoo and the AI providers you choose. Add a provider, paste your own API key, and any Odoo app or custom module can call that model through one method, with the same logging and limits everywhere.
The point is control. Each provider has a hard monthly token cap that is checked before a call is sent, so a runaway script or a busy month can't produce a surprise bill. Every call is recorded with the user, model, feature, linked record, tokens, duration and result, so you can see exactly where AI is used and what it costs.
Keys stay with managers: AI users can use the providers but never see the keys. It works in multi-company databases, with separate providers, keys, caps and usage per company. You pay the AI providers directly at their prices; AI Base adds no subscription and no commission on usage.
OpenAI, Anthropic Claude, Google Gemini, xAI Grok, Azure OpenAI, Mistral, Cohere, Perplexity and NVIDIA NIM. Pick a provider, paste your key, and a sensible default model is filled in. Any model the provider offers can be entered.
Limit input and output tokens per provider per month. The cap is checked before a call is sent, not after the bill arrives. Zero means unlimited.
Provider, model, user, feature, linked record, tokens, duration and status, with list, graph and pivot views for reporting.
Sends a tiny prompt to confirm the key and model work before anyone relies on them.
Two access groups: AI users can call providers; only AI managers can add providers and enter or see keys.
Send PDFs and images (JPEG, PNG, WebP, TIFF). Photos are rotated upright and resized to 2,400 px before sending, which keeps token use down.
Pass a JSON schema and get back a Python dict, ready to write into Odoo fields without parsing free text.
Override the base URL to route through a proxy or gateway, or to use self-hosted models on Ollama, vLLM or NVIDIA NIM.
Install AI Base
Install ki_ai_base from Apps. An AI Providers menu appears.
Add a provider
Go to AI Providers › Providers › New, choose the provider and paste your API key.
Set a cap and test
Enter a monthly token cap and click Test Connection.
Give people access
In Settings › Users, give staff the role AI Providers: User or AI Providers: Manager.
No. You use your own API keys and pay the AI providers directly at their prices. There is no subscription and no commission.
Calls to that provider stop until the next month or until a manager raises the cap. The cap is checked before each call is sent, so you are never billed past it.
Yes. Call _generate() on a provider record. It raises BudgetExceeded when the cap is reached, ProviderBusy for temporary failures you can retry, and UserError for permanent ones. Usage is logged automatically.
Yes. Set the base URL to your Ollama, vLLM or NVIDIA NIM endpoint, or to a gateway or proxy.
Yes. Providers, keys, caps and usage are kept per company, with record rules.
Buying from us directly suits invoices in your company's name, several databases, or help with installation. We reply with a quote within one business day. Card checkout comes later.
