Pricing
One credit is one Telegram Star. You see the price before every confirmation, and exactly that amount is charged.
7
per week
For fast images, no card.
1 · one fast image
Tiers
Packs
7501 5002 500Purchased credits never expire. It is one balance, not a plan.
The models
Every model on the shelf today, with what the cheapest run of it costs. You pick the one you want; a subscription never unlocks or locks any of them.
Images
Nano Banana 2
Google's flagship image model. It draws from a description and reworks whatever you send it, and text inside the frame comes out readable, which most models still cannot manage.
GPT Image 2
OpenAI's image model reads a long prompt closely and keeps things where you asked for them. Good when the frame needs legible text or a scene built exactly to description.
FLUX.1 Schnell
The quick draft model: you type a prompt and it draws it. Take it when you want to run through a dozen ideas rather than polish one.
Nano Banana Pro
The bigger Nano Banana: 2K output, clean text inside the frame, and edits that keep the detail. It works from a photo or from a prompt alone.
Seedream 5 Pro
ByteDance's photo editing: it swaps clothes, backgrounds and style without redrawing the person. It will not start without a photo, text alone is not enough.
Pruna P-Image
The fastest image here and one of the cheapest. Take it when you want to run through a dozen ideas rather than polish one.
Nano Banana 2 Lite
Google's editor: attach a photo, say what to change in plain words, and the face and the light survive it. Leave the photo out and it just generates from the prompt.
Seedream 5 Lite
The junior Seedream: the same grasp of a complicated scene as the Pro, at a fraction of the price. Strong on keeping a frame internally consistent.
Grok Imagine Image
xAI's image model in three quality rungs. The bottom one costs almost nothing; the top one reaches for the flagships.
FLUX.2
Black Forest Labs' current line, in three rungs. It bills by megapixel, so the frame here is pinned at exactly one.
FLUX.1 Kontext
The editing model people mean when they say editing: it holds a face and a style from frame to frame, which is why it is used on series rather than single images.
Qwen Image 3.0 Pro
Alibaba's flagship. One of the strongest in the world on blind comparisons, and inexpensive with it.
Recraft V4.1
Recraft for design work: clean graphics, careful typography, a result you can predict.
Krea 2
Krea in three rungs, from very fast to large. It has an aesthetic of its own, which is what people come to it for.
Pruna P-Image Edit
Edits a photo you send from a written instruction: swap the background, the style, one detail. The cheapest edit on the shelf.
Pruna Upscale
Raises a photo's resolution and cleans up the noise. Tens of times cheaper than the professional upscaler, because the output size is one we pin rather than one your file decides.
Recraft Vector
The only model here that returns real SVG rather than pixels. Logos and icons that scale to any size afterwards.
GPT Image 1.5
OpenAI's previous image engine, in two quality rungs. Cheaper than the current one and still in the world's top ten.
Recraft V4.1 Pro
The senior Recraft, for work that goes into production rather than into a chat.
Topaz Upscale
It enlarges an image four times and pulls detail back out instead of stretching pixels. For old photos and small screenshots you need to print or show large.
Video
Seedance 2.0
ByteDance's flagship: it holds a character and a scene from shot to shot instead of rebuilding them every second. It comes in 720p, 1080p, and an edit pass over video you already have.
Pruna P-Video
The cheapest video here. The draft rung costs less than the free weekly allowance, which means your first video need not cost you anything at all.
Wan 3.0
First in the world on blind text-to-video comparisons, and a third the price of the flagship we used to lead with.
Veo 3.1 Fast
Google's video model with sound, and the sound is real speech rather than dubbed-in effects. The only model here that does it.
Hailuo 2.3 Fast
The quick branch of Hailuo: it turns a photo into six seconds of movement, and the prompt is optional. It needs an actual photo, text alone will not start it.
Kling 3 Pro
Kling 3 Pro writes the sound along with the clip: footsteps, room tone, atmosphere. It starts from a photo and gives the cleanest motion in the Kling line.
Grok Imagine Video
xAI's video model: a photo becomes a five-second scene, and a clip you already have becomes a new version of itself. What you attach decides which of the two you get.
Seedance 2.0 Mini
The small Seedance: the same feel for movement as the flagship, in a single 720p rung driven by text. For drafts and for testing an idea before you run the bigger model.
Hailuo 2.3
The same Hailuo, but it starts from text: describe the scene and get six seconds. It keeps the physics honest, so people and objects move the way you expect.
PixVerse V6
Inexpensive video with sound. The middle ground for when Veo is too dear and a draft is not enough.
Kling 2.1 Standard
Classic Kling: it turns a photo into a five-second clip with a smooth camera move. The workhorse for when you want movement without surprises.
Pruna Avatar
One photo plus a script, and the person in the photo says it. Thirty voices to choose from.
Voice-over
ElevenLabs v3
ElevenLabs at its most expressive: you hear pauses, intonation and emotion instead of a robot. For voiceover and anything a person will listen to end to end.
OpenAI TTS
OpenAI's text to speech: an even voice and clear diction, nothing to set up. The plain option for long text, where being understood matters more than acting.
Grok TTS
Text to speech from xAI, at the cheapest price on the shelf.
MiniMax Speech 2.8 HD
Studio-grade narration with control over delivery and emotion. It sounds good in Russian.
ElevenLabs Flash v2.5
The speed model in the ElevenLabs line: it says short lines cleanly with nothing to configure. Take it for dialogue and reactions, not for half an hour of reading aloud.
Voice cloning
MiniMax Voice Clone
It takes a voice off a recording and turns it into one you can speak text with. It needs a clean sample, no music and nobody else in the background.
Star prices track model costs and can change. A change never applies to a generation already running.
Bought outside the app, Stars usually cost a little less.