Everything free. Upgrade when you're ready.

Every plan — Free included — gets the orchestrated modes: Maestro (Qwen 3.7 Plus conductor for daily work), Supernova (DeepSeek V4 Pro coordinator + V4 Flash specialists with Qwen builders for heavy multi-step work), Aurora (Mistral-only EU stack for GDPR-strict and sovereign workloads), and Longxiang (Kimi K3 coordinating and building, with Qwen 3.7 Plus and DeepSeek V4 Flash beneath it — the strongest agentic-coding fleet we run). You also get the single models those fleets are built from — Qwen 3.7 Max / 3.7 Plus / 3.5 Flash, DeepSeek V4 Pro / V4 Flash, Mistral Medium 3.5 / Small 4 / Large 3, Kimi K3 / K2.7 Code — pickable one at a time and billed at that model's own credit rate. Plus Creative Studio for image, audio, speech, and video. Free and Paid share identical features — we only charge for more credits, nothing is locked. With your own API keys you can add anything else on top (Claude, GLM, or any OpenAI-compatible provider), and those requests cost no credits at all.

A mode when you want the work handled, a single model when you know what you want. Maestro = predictable daily cost on a single Qwen conductor. Supernova = a frontier-tier coordinator (DeepSeek V4 Pro) directing Qwen specialists for heavy multi-step work. Aurora = the entire stack stays inside the EU on Mistral weights, GDPR-strict and sovereign by default. Pick a single model instead and it still runs inside Ava — that one model fills every persona seat, so you keep the specialist pipeline with one brain doing all of it. A pricier model therefore costs more per turn, which is why each one carries its own credit rate.

Yes — BYOK gets the same modes, gated by the keys each fleet needs. Add a Qwen key to unlock Maestro. Add Qwen + DeepSeek to unlock Supernova. Add Mistral to unlock Aurora. You can also drive any individual model your keys cover (Claude, Kimi, GLM, etc.). BYOK requests don't consume your credit allowance — you pay the provider directly.

No. The Free tier works entirely with your own API keys and doesn't require an account. Just install the extension, add an API key from any provider, and start working. You only need an account for managed plans.

Yes. Even on Pro, Ultra, or Enterprise, you can use your own API keys alongside your credit allowance. BYOK requests don't consume credits. Best of both worlds.

Purchase top-ups anytime without changing your plan. Top-up credits don't expire — they carry over until used.

One credit is a unit of value, not a raw token count. Simple actions like a chat turn cost 2 credits; light routing or classification costs 1. Heavier work costs more — a full orchestrated task is around 10 credits, image generation is 12, music 50, video 150. Creative Studio voice is 10. Teach mode bills as standard chat turns (2 credits). Premium reasoning models add a multiplier on top — V4 Pro costs 6× the base. Cache-hit responses charge less automatically. You see the credit counter tick down in real time.

Simple — one pool, one number. Every managed request (Maestro / Supernova / Aurora chat, plus Creative Studio) deducts from your credit allowance. The allowance resets each billing period. No separate pools, no confusion.

Yes! If you use your own API keys and love what we're building, support us through GitHub Sponsors. Every contribution helps keep Ava open-source and free for everyone.

Yes. No contracts, no commitments. Cancel anytime from your dashboard.