Everything free. Upgrade when you're ready.
61 tools, 6 modes, 24 personas, 5-layer memory — every feature on every plan. You only pay for more tokens and more storage.
- 3M tokens / mo
- 2 GB cloud
- BYOK — any provider
No account required with your own keys
Download- 15M tokens / mo
- 25 GB cloud
- All managed models
No keys needed — we handle it
Coming Soon- 40M tokens / mo
- 100 GB cloud
- Extended context + early access
For power users
Coming Soon- 100M tokens / mo
- 500 GB cloud
- SSO + priority support
Team-scale usage
Coming SoonToken top-ups
one-time3M
$3
$1/M
10M
$8
$0.80/M
25M
$15
$0.60/M
Tokens carry over until used.
Storage add-ons
recurring+50 GB
$3
per month
+250 GB
$12
per month
+1 TB
$45
per month
Stacks on top of your plan. Cancel anytime.
All paid plans & add-ons launch April 17th
Have a coupon code?
What runs on each plan
Every plan gets every model and every feature. We only charge for tokens and storage — nothing is locked behind a paywall.
Free
3M tokens / 2 GB storage per month
- Qwen 3.6 Plus— conductor
- Qwen 3.5 Omni Plus— vision + reasoning
- Qwen 3.5 Plus— 1M context
- Qwen Omni Flash— free tier default
- Qwen Flash— fast + cheap
- Creative Studio— image, audio, speech, video (MiniMax)
Paid
More tokens, more storage — same features
- Qwen 3.6 Plus— conductor
- Qwen 3.5 Omni Plus— vision + reasoning
- Qwen 3.5 Plus— 1M context
- Qwen Omni Flash— free tier default
- Qwen Flash— fast + cheap
- Creative Studio— image, audio, speech, video (MiniMax)
BYOK — any plan
Your keys, no allowance consumed
- Anthropic (Claude)
- DeepSeek
- Mistral
- Moonshot (Kimi)
- Zhipu (GLM)
- MiniMax — required for Creative Studio
- or any OpenAI-compatible endpoint
Cost Calculator
Pick a model, set your usage, see what it costs.
Included on managed plans
BYOK — your keys, any plan
Managed
Qwen 3.6 Plus
conductor
Estimated monthly
$2.40
Usage
4.5M tok
Input
$0.60
$0.20/M
Output
$1.80
$1.20/M
Your 4.5M projected usage fits on the Pro plan at $19/mo (15M token allowance) — no per-token charges on top.
Frequently Asked Questions
What models are included on managed plans?
Every plan — Free included — gets the full Qwen line-up (3.6 Plus, 3.5 Omni Plus, 3.5 Plus, Omni Flash, Flash) and Creative Studio on MiniMax for image, audio, speech, and video. Free and Paid have identical features — we only charge for more tokens and more storage, nothing is locked. With your own API keys, you can add Claude, DeepSeek, Mistral, Kimi, Zhipu, MiniMax, or any OpenAI-compatible provider on any plan.
Why Qwen for the models and MiniMax for Creative Studio?
Qwen 3.6 Plus leads on agentic coding — Terminal-Bench #1, 1M context, native function calling. Auto Mode routes every coding request across the Qwen family to match the task. Creative Studio is a different problem — image, audio, speech, and video — and MiniMax is best-in-class there. Each provider plays to its strength.
Can I use Claude, DeepSeek, Mistral, etc.?
Yes. On any plan including Free, bring your own API keys — Kimi, Anthropic, DeepSeek, Moonshot, MiniMax, Zhipu, Mistral, or any OpenAI-compatible endpoint. BYOK requests don't consume your plan's token allowance.
Do I need an account to use Ava?
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.
Can I bring my own API keys on a paid plan?
Yes. Even on Pro, Ultra, or Enterprise, you can use your own API keys alongside managed tokens. BYOK requests don't consume your plan allowance. Best of both worlds.
What happens if I run out of tokens?
Purchase top-ups anytime without changing your plan. Top-up tokens don't expire — they carry over until used.
What happens if I run out of cloud storage?
Cloud sync pauses for new uploads, but your local work keeps going exactly as normal — Ava is local-first by design. You can free up space, add a storage top-up (+50 GB/$3, +250 GB/$12, +1 TB/$45 per month), or upgrade your plan. Nothing is ever deleted without your permission.
Is storage the same as tokens?
No. Tokens are consumed-and-gone — they power inference (Ava thinking). Storage accumulates — it holds your memories, chat history, generated media, and synced files across devices. Different cost shapes, priced separately.
Does BYOK count against my storage allowance?
No. BYOK users are fully local — zero platform storage, zero telemetry. The cloud allowance only applies when you opt into cloud sync with managed plans. If privacy matters, BYOK is the path.
How does the single token pool work?
Simple — one pool, one number. Every managed request (Qwen models, MiniMax Creative Studio) deducts from your token allowance. The allowance resets each billing period. No separate pools, no confusion.
Can I donate to support the project?
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.
Can I cancel anytime?
Yes. No contracts, no commitments. Cancel anytime from your dashboard.
Powered by Qwen
Qwen 3.6 Plus is the conductor — 1M context, native function calling, Terminal-Bench #1 for agentic coding. Auto Mode routes across the Qwen family to match the task. Creative Studio runs on MiniMax. Frontier performance at a fraction of the cost, with a 50% enterprise pricing partnership baked in.
Support Ava
Using your own API keys and love what we're building? Your support keeps Ava open-source and helps us add new providers and features for everyone.
Local-first is sacred
Every feature works without an account. Every conversation, every memory, every piece of generated content lives on your machine first. Cloud sync is additive — never the master.
BYOK users stay fully local. Zero platform storage, zero telemetry, zero reporting. If privacy is the point, BYOK is the path.