One honest unit, every action

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.

300 free / monthBYOK unlimitedNo feature gatingPremium = multiplierCache-hit discount

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.

three modes · three credit shapes

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

ActionCredits
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
On Pro: ~1,000 chat turns / month on Pro

Supernova

Heavy multi-step · frontier coordinator

DeepSeek V4 Pro · V4 Flash · Qwen builders

ActionCredits
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
On Pro: ~2,500 chat turns / month on Pro

Aurora

EU sovereign · Mistral end-to-end

Mistral Large 3 · Medium 3.5 · Small 4

ActionCredits
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
On Pro: ~600 chat turns / month on Pro
single-model rates

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.

ProviderModelChat turnMultiplier
QwenQwen 3.6 Plus30.7×
QwenQwen 3.5 Plus30.6×
QwenQwen 3.5 Omni Plus30.6×
QwenQwen 3.5 Omni Flash11.0×
QwenQwen 3.5 Flash11.0×
DeepSeekDeepSeek V4 Pro153.75×
DeepSeekDeepSeek V4 Flash20.5×
MistralMistral Large 351.25×
MistralMistral Medium 3.5174.25×
MistralMistral Small 430.6×

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.

creative studio · same on every mode

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.

12
credits
Image generation
Wan — graphic-design grade, vector / icon / banner output
150
credits
Video generation
MiniMax Hailuo 02 Pro — 6-second 1080p clip
50
credits
Music generation
MiniMax Music — full track
10
credits
Voice generation
MiniMax Speech 2.8 HD — ~500 chars
2
credits
Background removal
Image cleanup

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.

5,000 credits / month

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.

💬
~1,000 Maestro chat turns
Daily-driver Maestro on Qwen 3.6 Plus — predictable, fast, the everyday lane
~2,500 Supernova turns
V4 Flash chat / V4 Pro orchestration when the work warrants it
🇪🇺
~600 Aurora turns
Sovereign EU stack — Mistral Large 3 chat / Medium 3.5 specialists
🖼️
~415 images
Design iterations, hero art, diagrams — Wan graphic-design grade

Every plan gets everything.

We never lock features behind tiers. The only things that scale are credits and cloud storage.

Every model we host
Full Qwen lineup (3.6 Plus → Flash) for chat and code, MiniMax for Creative Studio
Every tool
File ops, shell, git, web, memory, learning, documents — all tools on all plans
Every mode
Work, Plan, Chat, Teach, Security, Brainstorm — all six, free tier included
Every persona
24 specialists across the 5 non-Chat modes, orchestrated by Conductor
5-layer memory
Extract · Reflect · Accumulate · Analyse · Consolidate — across every session
Creative Studio
Image, video, music, voice, background removal — same credits pool
bring your own key

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.
try it. keep it. or bring your own keys.

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.