Ava Supernova
AvaSupernova
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.

each fleet · its own credit shape

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. Longxiang puts Kimi K3 in both the coordinator and Builder seats when the work earns it. Pick the mode for the job; the per-action cost reflects the fleet that runs it.

Maestro

Daily work · predictable cost

Qwen 3.7 Plus · Omni Plus · 3.5 Plus · 3.5 Flash

ActionCredits
Chat turn
Qwen 3.5 Flash chat tier (0.22× multiplier)
1
Plan creation
Health / nutrition plan in Chat mode — billed as a chat turn
1
Light classifier
Qwen 3.5 Flash intent gate
1
Heavy persona
Architect / Builder on Qwen 3.7 Plus (0.51× multiplier)
2
Light persona
Scout / Verifier on Flash
1
Full orchestration
Qwen 3.7 Plus coordinates · Architect + Builder · 3 light specialists
9
On Pro: ~5,000 chat turns / month on Pro

Supernova

Heavy multi-step · frontier coordinator

DeepSeek V4 Pro · V4 Flash · Qwen 3.7 Plus + 3.5 Omni

ActionCredits
Chat turn
DeepSeek V4 Flash · fast chat tier (0.37× multiplier)
1
Plan creation
Health / nutrition plan in Chat mode — billed as a chat turn
1
Light classifier
Qwen 3.5 Flash intent gate
1
Heavy persona
Qwen 3.7 Plus Builder spawn (0.51× multiplier)
2
Light persona
Qwen 3.5 Flash specialists
1
Full orchestration
V4 Pro coordinates · Qwen Builder · V4 Flash specialists
9
On Pro: ~5,000 chat turns / month on Pro

Aurora

EU sovereign · Mistral end-to-end

Mistral Medium 3.5 · Small 4 · Large 3

ActionCredits
Chat turn
Mistral Small 4 chat tier (0.85× multiplier)
2
Plan creation
Health / nutrition plan in Chat mode — billed as a chat turn
2
Light classifier
Mistral Small 4 intent gate
1
Heavy persona
Mistral Medium 3.5 (Builder · vision · long-form) — 3.12× multiplier
9
Light persona
Mistral Small 4 specialists
1
Full orchestration
Medium 3.5 coordinates + builds · Small 4 specialists · Large 3 heavy reserve
28
On Pro: ~2,500 chat turns / month on Pro

Longxiang

Open weights · strongest coder

Kimi K3 · Qwen 3.7 Plus · DeepSeek V4 Flash

ActionCredits
Chat turn
DeepSeek V4 Flash · fast chat tier (0.37× multiplier)
1
Plan creation
Health / nutrition plan in Chat mode — billed as a chat turn
1
Light classifier
DeepSeek V4 Flash intent gate
1
Heavy persona
Kimi K3 (coordinator AND Builder) — 6.24× multiplier, the priciest model we serve
19
Light persona
DeepSeek V4 Flash specialists
1
Full orchestration
K3 coordinates AND builds · Qwen 3.7 Plus mid-tier + vision · V4 Flash specialists
54
On Pro: ~5,000 chat turns / month on Pro — but only ~80 full orchestrations. BYOK uses no credits at all.
single models · one at a time, on credits

Or drive a single model.

The fleets are the recommendation, but on a signed-in account you can pick one model directly — no key needed — and it runs on credits. It still runs inside Ava's system: on Platform that one model fills every persona seat (coordinator, Architect, Builder, specialists), so a pricier model costs more per turn. Bring your own key instead and it draws no credits at all.

ModelProviderVision~Credits / message
Qwen 3.5 Flash
0.22× rate
Qwen1
Qwen 3.7 Plus
0.51× rate
Qwen1
Qwen 3.7 Max
3.22× rate
Qwen6
DeepSeek V4 Flash
0.37× rate
DeepSeek1
DeepSeek V4 Pro
0.66× rate
DeepSeek1
Mistral Small 4
0.85× rate
Mistral2
Mistral Large 3
0.92× rate
Mistral2
Mistral Medium 3.5
3.12× rate
Mistral6
Kimi K2.7 Code
1.68× rate
Moonshot3
Kimi K3
6.24× rate
Moonshot12

“~Credits / message” is an illustrative short turn (one 16K bracket); real turns scale in whole brackets exactly like the fleet tables above. The rate is the model's cost multiplier — what it genuinely costs us, at a 30% margin. Single-model picking on credits needs a signed-in account; on your own key it's unlimited and draws no credits.

creative studio · same on every mode

Every asset the Studio makes.

The mode you're in doesn't change Creative Studio pricing — same rate whether you're running Maestro, Supernova, or Aurora.

20
credits
Icon generation
A clean, on-brand vector icon
20
credits
Logo generation
A full logo system — mark, real-font wordmark, and every lockup
12
credits
Image generation
Wan — graphic-design grade hero art, illustration and banners
150
credits
Video generation (720p)
Wan 2.5 — 720p clip (5s or 10s) with synchronized audio
300
credits
Video generation (1080p)
Wan 2.5 — full-HD 1080p clip with synchronized audio
10
credits
Voice generation
Qwen3-TTS — natural narration, ~500 chars
2
credits
Background removal
Transparent-background cleanup — bundled into icon generation
TBD
soon
App Icon / Favicon
Full app-icon set + favicon, every size
TBD
soon
Badge / Mark
Standalone badges and marks
TBD
soon
Avatar
Profile and brand avatars
TBD
soon
Banner
Site and social banners
TBD
soon
Hero
Hero / feature imagery
TBD
soon
Social / OG Image
Share cards and OG images
TBD
soon
Illustration
Custom illustrations
TBD
soon
Pattern / Background
Seamless patterns and backgrounds
TBD
soon
Concept Art
Game concept art
TBD
soon
Character / Portrait
Characters and portraits
TBD
soon
Creature / Enemy
Creatures and enemies
TBD
soon
Ability Icons
Skill and ability icons
TBD
soon
Item / Prop
Items and props
TBD
soon
Card
Game and trading cards
TBD
soon
Environment / Background
Environments and backgrounds
TBD
soon
Key Art / Splash
Key art and splash screens
TBD
soon
World Map
World and level maps
TBD
soon
Emblem / Crest
Emblems and crests
TBD
soon
Texture / Material
Tiling textures and materials
TBD
soon
Tileset
Tilesets
TBD
soon
Sprite
Sprites and sprite sheets

The figures above are for a short turn — one 16K bracket. Longer turns scale in whole brackets: effective tokens = input + (output × 4), divided into 16K blocks. A 16K-input, 2K-output turn is 24K effective, so it's 2 brackets and costs double the numbers shown. 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. Per-turn input cap: Free 16K · Pro 128K · Ultra 256K · Enterprise 512K — a single runaway turn can't drain a month's allowance.

health & plans · same on every mode

Recipes, workouts, briefs.

Starting a health or nutrition plan bills as a single chat turn. Filling it out — every recipe and exercise Ava generates into it — is flat-priced below, so a full plan's cost is never a surprise.

2
credits
Recipe generation
Each recipe Ava generates into a meal plan
2
credits
Exercise generation
Each exercise Ava generates into a workout plan
1
credit
Morning brief
Your daily health + nutrition brief
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 3.7 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 thing that scales is credits.

Every model we host
Full Qwen lineup (3.7 Plus → Flash) for chat and code, Wan for images and video, Qwen3-TTS for voice
Every tool
File ops, shell, git, web, memory, learning, documents — all tools on all plans
Every mode
Code, Plan, Chat, Teach, Security, Brainstorm, Write — all seven, 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
Icon, logo, image, video, 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 — 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.