A credit is a credit is a credit.
Tokens never mapped to anything predictable — 1M tokens on one model isn't 1M on another. Credits abstract the action you took (chat turn, orchestration, image), and a model multiplier on top scales the cost so premium reasoning models track their actual per-token spend. You always know what a turn will cost before you spend it.
Why selling tokens was dishonest
1M tokens isn't 1M tokens.
Context windows, prompt caches, and input/output pricing all differ by provider. “15M tokens/month” was selling you a number that didn't predict a single session.
Costs shifted under you.
Every provider price tweak would silently move how far your allowance stretched. You couldn't plan around it because we couldn't either.
Actions matter, not tokens.
You don't care how many tokens a chat turn used — you care that you asked a question and got an answer. We priced around the thing you actually wanted.
Pick the work, the price falls out of that.
Maestro is the daily driver — cheap, predictable, fast. Supernova lights up frontier reasoning when the work warrants it. Aurora keeps everything inside the EU on Mistral weights. Pick the mode for the job; the per-action cost reflects the fleet that runs it.
Maestro
Daily work · predictable cost
Qwen 3.6 Plus · Qwen 3.5 Flash
| Action | Credits |
|---|---|
Chat turn Qwen 3.6 Plus coordinator | 3 |
Light classifier Qwen 3.5 Flash intent gate | 1 |
Heavy persona Architect / Builder on Qwen 3.6 Plus | 4 |
Light persona Scout / Verifier on Flash | 1 |
Full orchestration Conductor + 4–6 personas | 14 |
Supernova
Heavy multi-step · frontier coordinator
DeepSeek V4 Pro · V4 Flash · Qwen builders
| Action | Credits |
|---|---|
Chat turn DeepSeek V4 Flash · fast chat tier | 2 |
Light classifier Qwen 3.5 Flash intent gate | 1 |
Heavy persona Qwen 3.6 Plus Builder spawn | 4 |
Light persona Qwen 3.5 Flash specialists | 1 |
Full orchestration V4 Pro coordinates · Qwen + V4 Flash specialists | 38 |
Aurora
EU sovereign · Mistral end-to-end
Mistral Large 3 · Medium 3.5 · Small 4
| Action | Credits |
|---|---|
Chat turn Mistral Large 3 coordinator-direct | 5 |
Light classifier Mistral Small 4 intent gate | 1 |
Heavy persona Mistral Medium 3.5 (Builder · vision · long-form) | 13 |
Light persona Mistral Small 4 specialists | 1 |
Full orchestration Large 3 coordinates the three-tier fleet | 13 |
Pick a single model directly.
When you want to drive one model without orchestration — frontier on every turn, or flash on every turn, your call. The rate per chat turn at a typical 16K + 2K token shape, with the cost multiplier that scales it.
| Provider | Model | Chat turn | Multiplier |
|---|---|---|---|
| Qwen | Qwen 3.6 Plus | 3 | 0.7× |
| Qwen | Qwen 3.5 Plus | 3 | 0.6× |
| Qwen | Qwen 3.5 Omni Plus | 3 | 0.6× |
| Qwen | Qwen 3.5 Omni Flash | 1 | 1.0× |
| Qwen | Qwen 3.5 Flash | 1 | 1.0× |
| DeepSeek | DeepSeek V4 Pro | 15 | 3.75× |
| DeepSeek | DeepSeek V4 Flash | 2 | 0.5× |
| Mistral | Mistral Large 3 | 5 | 1.25× |
| Mistral | Mistral Medium 3.5 | 17 | 4.25× |
| Mistral | Mistral Small 4 | 3 | 0.6× |
BYOK requests don't consume platform credits — pay your provider directly, Ava just orchestrates. The rates above apply when you pick the model on a managed plan and credits cover the call.
Image, video, music, voice.
The mode you're in doesn't change Creative Studio pricing — same rate whether you're running Maestro, Supernova, or Aurora.
Cache-hit discount: when the provider reports a prompt-cache hit on a chat turn, you pay 0.3× the normal cost (minimum 1 credit) — 0.5× on output-heavy models like V4 Pro. Long-context turns scale: under ~16K effective tokens you charge the flat rate, beyond that credits scale linearly. Per-turn input cap: Free 16K · Pro 128K · Ultra 256K · Enterprise 512K — a single runaway turn can't drain a month's allowance.
What Pro feels like in a month.
Real work mixes actions — these are the “enough for” ceilings if you spent your whole month on one thing. Mix and match as you actually work.
Every plan gets everything.
We never lock features behind tiers. The only things that scale are credits and cloud storage.
BYOK is a separate path.
Connect your own API key from any provider — Anthropic, Moonshot, DeepSeek, Mistral, Zhipu, Qwen, MiniMax — and those calls don't touch your credit balance. You pay the provider directly; Ava just orchestrates.
- Credits are for the platform. Chat turns, Creative Studio, orchestration on the models we host.
- BYOK is for your own keys. Unlimited by whatever your provider charges. Credits stay untouched.
- You can do both. Use platform credits for the models we host, BYOK for everything else, in the same session.
300 credits a month, to try.
No card needed. Enough to evaluate the full platform — every model, every tool, every mode. When you're ready for real daily use, upgrade to Pro for 5,000 credits/month, or bring your own API key for unlimited usage on any provider. Free tier resets every month, forever, no trial clock.