Skip to content Skip to the trial run

Veo, Kling, Seedance, Nano Banana
all image and video AI in one place.

One window and one balance for image, video and voice models. No subscription required: you are charged only for what you actually create.

NetRoom is a platform for generating images, video and sound: Veo, Kling, Seedance, Nano Banana, ElevenLabs and the rest of the catalog run in one window on a single balance. You pay per finished frame, no subscription required, and signing up is free. Payment is in USD or EUR. Text models — ChatGPT, Claude, Gemini — are here too, on the same balance.

Free: 3 images per day after signing in with Google or Telegram · no card required · pay in USD or EUR

NetRoom is a platform for generating images, video and sound: Veo, Kling, Seedance, Nano Banana, ElevenLabs and the rest of the catalog run in one window on a single balance.

More

You pay per finished frame, no subscription required, and signing up is free. Payment is in USD or EUR. Text models — ChatGPT, Claude, Gemini — are here too, on the same balance.

71 models for image, video and sound
each one priced in the catalog
from $0.023 per image
catalog price, listed below
3 per day images free
after signing in with Google or Telegram
$0 required subscription
you pay per finished frame
Images

An image from $0.023.

The model sets the look of a frame and its price. Pick a model in the list: next to it is its result on a real prompt and the price of a frame like it.

Frame price, cheapest to priciest
Seedream 4.5: Wide cinematic shot of a tiny red tram crossing a vast snowy mountain valley at blue hour, warm glowing window
Seedream 4.5
Model
$0.048Frame price
Prompt

Wide cinematic shot of a tiny red tram crossing a vast snowy mountain valley at blue hour, warm glowing windows, long soft shadows on the snow, pine forest on the slopes, matte painting style, ultra detailed

Make one like it

The price of one image on this model at today's rates.

Video

Video is counted in seconds.

A clip costs its duration times the price of a second at its resolution. Pick a clip: its price at today's rates is next to it.

Grok Imagine Video 1.5 Lite: A paper boat drifting down a rain-soaked city street at night, neon signs reflected in the puddles, gentle sou
Grok Imagine Video 1.5 Lite
4 s × $0.024 per second · 480p
$0.10Clip price
Prompt

A paper boat drifting down a rain-soaked city street at night, neon signs reflected in the puddles, gentle sound of rain

Price at current rates: file duration times the price of a second at its resolution, without sound. The exact amount is shown in the editor before you run anything.

The player starts muted; use the volume button to turn sound on.

Voice
Voice Clone

New words.
Your voice.

Narrate videos, stories and greetings with your voice. Record a sample or upload audio, then use it for your next script.

Try Voice Clone

In Sound, choose “Clone your voice”. Voice cloning guide

Voice-over pricing depends on the model and text length.

  1. Your sample

    Record with your microphone or upload an audio file.

  2. New words

    A video script, a passage from a book or a greeting.

  3. Your voice-over

    Listen to the result and use it in your project.

Available withFish Audio S2.1 ProHeyGen VoiceHeyGen Voice TurboFish Audio Drama 3

Or choose a ready-made voice

Voice from $0.00038 a phrase.

Tap a voice. The same phrase, different models. Next to it is the price of such a voice-over.

Hello! This is how my voice sounds. I will read your text clearly and naturally.

Price for this phrase

  • NadineHeyGen Voice Turbo · 0:06
    $0.00038for this phrase · 0:06
  • LauraFish Audio Drama 3 · 0:05
    $0.00096for this phrase · 0:05
  • Voice 3150Mistral Voxtral TTS 3 · 0:05
    $0.0012for this phrase · 0:05
  • AntonioluisAssemblyAI TTS 1 · 0:06
    $0.0014for this phrase · 0:06
  • cs-CZ-GrantMicrosoft MAI-Voice 2.1 Flash · 0:06
    $0.0014for this phrase · 0:06
  • EvexAI TTS · 0:05
    $0.0014for this phrase · 0:05
  • LorettaInworld Realtime TTS-2 · 0:06
    $0.0034for this phrase · 0:06

A minute of speech is roughly 850 characters.

Your month

Build your month.

The sliders use the catalog prices: what a month of images, video and voice-over comes to.

Prices by task. The month calculator itself needs JavaScript.

Here one balance covers 71 models, and what you do not spend does not expire. Video is counted at the model's minimum resolution and without sound.

Top up

Top up once, spend on any model.

Your balance never expires and there is no auto-renewal. A pack beats small top-ups: the token bonus grows with the amount.

Mini
$5
490 tokens
≈ enough for
  • ≈ 54 GPT-6.1 Sol requests
  • ≈ 840 Auto requests
  • ≈ 50 Nano Banana 2 images
  • ≈ 72 SeeDream 4.5 images
  • ≈ 21 Nano Banana Pro images
  • ≈ 270 sec of Kling VIDEO 3.0 Standard video
  • ≈ 200 sec of Kling VIDEO O3 Pro video
Buy
Standard
$17
1639 tokens +10%
save 9%
≈ enough for
  • ≈ 180 GPT-6.1 Sol requests
  • ≈ 2800 Auto requests
  • ≈ 160 Nano Banana 2 images
  • ≈ 240 SeeDream 4.5 images
  • ≈ 71 Nano Banana Pro images
  • ≈ 900 sec of Kling VIDEO 3.0 Standard video
  • ≈ 600 sec of Kling VIDEO O3 Pro video
Buy
Max
$111
11988 tokens +20%
save 17%
≈ enough for
  • ≈ 1300 GPT-6.1 Sol requests
  • ≈ 20000 Auto requests
  • ≈ 1200 Nano Banana 2 images
  • ≈ 1700 SeeDream 4.5 images
  • ≈ 520 Nano Banana Pro images
  • ≈ 6600 sec of Kling VIDEO 3.0 Standard video
  • ≈ 4900 sec of Kling VIDEO O3 Pro video
Buy

or a budget subscription for generation

Student
For studies: notes, essays and presentation visuals
$5.44 / 30 days

Model groups

Fast text300 requests per 30 daysUp to 15 per day

Shared by all models in this group

  • DeepSeek V4 Pro
  • DeepSeek v4.1 FlashFree model
Study text120 requests per 30 daysUp to 6 per day

Shared by all models in this group

  • Claude Haiku 5.5
  • Gemini 3.5 Flash LiteFree model
  • Kimi K3
  • Perplexity Sonar
  • GPT-6 LunaFree model
  • Gemini 3.8 Flash
Flagships6 requests per 30 daysUp to 1 per day

Shared by all models in this group

  • Claude Sonnet 5.5
  • GPT-6.1 Sol
  • Claude Opus 5.5

Individual model quotas

  • GPT-5 Image MiniImage generation in chat30 requests per 30 daysUp to 3 per day
  • GPT-5.4 Image 2Image generation in chat15 requests per 30 daysUp to 2 per day
  • Nano Banana 2Image generation in chat4 requests per 30 daysUp to 1 per day
How the limits work

The request quota covers the full 30-day paid period; the daily cap also applies.

Daily limits reset at 00:00 UTC; unused daily quota does not carry over.

After a daily or period limit, further requests are charged to your balance at the model's current rate.

Other models follow their usual terms: paid requests are charged separately; free models stay free.

These image quotas apply to the exact models listed in chat, not to similarly named Studio models.

Get the subscription
  • No subscription needed to start
  • Your pay-as-you-go balance stays — a plan sits on top
  • Subscription quotas are listed in the plan
Models

71 models. Each has a price.

One balance across Veo, Kling, Seedance, Nano Banana and another 67 models. No subscription required, and your balance does not expire: you are billed for results, not for the month.

Free every day

3 images per day on Google Nano Banana 2 Lite and Seedream 5.0 Flash. Requires a Google or Telegram account linked to your profile; without one the free limit stays off. Beyond the daily limit an image costs its usual price.

Try it free
Language
GPT-6 Astra
Flagship of the GPT-6 generation. 1M token context, text, image and file input.
In $0.015 / Out $0.075 / 1K
Language
GPT-6 Astra Pro
Same GPT-6 Astra weights served with pro reasoning. 1M token context.
In $0.015 / Out $0.075 / 1K
Language
GPT-6.1 Sol
OpenAI's high-end model below Astra: agentic coding, documents, 1.05M context
In $0.006 / Out $0.03 / 1K
Language
GPT-6.1 Terra
Clear writing, useful explanations and everyday coding assistance
In $0.003 / Out $0.015 / 1K
Language
GPT-6.1 Sol Pro
The same GPT-6.1 Sol served with pro reasoning for hard tasks. 1.05M context
In $0.006 / Out $0.03 / 1K
Language
GPT-6.1 Terra Pro
Extended reasoning for constraints, dependencies and solution checks
In $0.003 / Out $0.015 / 1K
Language
GPT-6 Luna
The most cost-efficient tier of the GPT-6 generation. 1M token context, text, image and file input.
Free
Language
GPT-6 Luna Pro
Same GPT-6 Luna weights served with pro reasoning. 1M token context.
In $0.0018 / Out $0.009 / 1K
Language
Perplexity Sonar
Questions about public information with links you can inspect
In $0.0028 / Out $0.0028 / 1K
Language
Auto Router Beta
Smart auto-router: automatically picks the best model for your prompt (beta)
In $0.0038 / Out $0.0225 / 1K
Language
Claude Fable 5.2
Review demanding code, technical decisions and long materials
In $0.012 / Out $0.06 / 1K
Language
Claude Opus 5.5
Anthropic's flagship for long-running agentic coding and knowledge work
In $0.0075 / Out $0.0375 / 1K
Language
Gemini 4 Carbon
Engineering problems, multi-step analysis and technical verification
In $0.003 / Out $0.015 / 1K
Language
Gemini 4 Argon
Google's flagship reasoning model for hard code, science and agents
In $0.003 / Out $0.015 / 1K
Language
Gemini 3.8 Flash
Google's Flash model for agents, coding and multi-step work
In $0.0011 / Out $0.0056 / 1K
Language
Gemini 3.5 Flash Lite
The most cost-effective model in the Gemini 3.5 line
Free
Language
Claude Haiku 5.5
Anthropic's small, fast model for high-volume work
In $0.0015 / Out $0.0075 / 1K
Language
Claude Sonnet 5.5
Anthropic's everyday model for code, documents, slides and spreadsheets
In $0.003 / Out $0.015 / 1K
Language
Grok 4.7
xAI frontier model for coding and agents. 500K context, text and image input.
In $0.0022 / Out $0.0067 / 1K
Language
Kimi K3
Connected code fragments, technical material and structured analysis
In $0.0044 / Out $0.021 / 1K
Language
Qwen3.8 Max
Development tasks, structured material and explicit assumptions
In $0.006 / Out $0.018 / 1K
Language
DeepSeek V4 Pro
Reasoning, olympiad math and code
In $0.0028 / Out $0.0111 / 1K
Language
DeepSeek v4.1 Flash
Fast free next-gen model
Free
Language
Qwen3.8 Flash
Fast multilingual model — free
Free
Language
Gemini 4 Hydrogen
Turn working material into clear everyday results
In $0.0023 / Out $0.0113 / 1K
Language
Ling 3.2 Flash
Study explanations, small calculations and constrained drafts
Free
Language
Hy4 flash
Everyday writing and clearly scoped tasks
In $0.0001 / Out $0.0002 / 1K
Language
Qwen4 Max
Multi-step work from requirements to a practical verification plan
In $0.0043 / Out $0.0128 / 1K
Image
Google Nano Banana 2 Lite
Nano Banana 2 Lite is Google’s model for creating images from a brief and making changes with a reference.
Free: 3 per day Image $0.042
Image
Seedream 5.0 Flash
Seedream 5.0 Flash is ByteDance’s model for generating images from a description and working with references.
Free: 3 per day Image $0.023
Image
GPT-Image-2.6 Flare
GPT-Image-2.6 Flare is a distinct OpenAI variant for generating and editing images.
Image $0.10
Image
GPT-Image-2.6 Sunburst
GPT-Image-2.6 Sunburst is an OpenAI image-model variant for detailed visual briefs and reference-guided changes.
Image $0.18
Image
Grok Imagine Image 2.0
Next-generation Grok image model for text-to-image and prompt-guided editing at 1K and 2K
Image $0.072
Image
Kling IMAGE 3.0
Kling image model: native 2K output, realistic textures and materials, image-to-image from a reference
Image $0.034
Image
Krea 2 Large
Larger Krea 2 variant for rawer, more flexible outputs with stronger photorealism and weighted reference control
Image $0.072
Image
Krea 2 Medium
Faster Krea 2 variant for stable, consistent generation with controllable prompt strength and weighted reference guidance
Image $0.036
Image
Krea 2 Turbo
Explore visual ideas with Krea 2 Turbo: images from descriptions, style references, moodboards and a choice of aspect ratios.
Image $0.052
Image
Nano Banana 2.1
Google's newest Nano Banana: image generation and editing at 1K/2K/4K with up to 14 reference images
Image $0.042
Image
Qwen-Image-3.0
Alibaba image model balancing quality and speed: generation, editing, multilingual typography, up to 3 references
Image $0.036
Image
Qwen-Image-3.0 Pro
Top-tier Qwen image model for dense layouts, small-text rendering and multilingual typography
Image $0.048
Image
Recraft V4 Pro
Design-grade images up to 2048x2048 with clean text and refined detail, ready for print
Image $0.30
Image
Recraft V4 Pro Vector
Editable SVG with clean geometry: icons, logos and illustrations at Pro quality
Image $0.36
Image
Recraft V4 Vector
SVG generator for icons, logos and simple illustrations
Image $0.096
Image
Riverflow 2.0 Fast
Fast image model for ads and product scenes: generation, edits and upscale that keep product shape and on-scene text sharp
Image $0.06
Image
Seedream 4.5
ByteDance image model: 2K to 4K output, up to 14 reference images, accurate text
Image $0.048
Image
Wan2.7 Image
Alibaba image model for generation and editing: palette control, region edits, multilingual text
Image $0.036
Image
Wan2.7 Image Pro
Alibaba Wan2.7 Image Pro: stronger composition, up to 4096 px, multilingual text
Image $0.09
Image
Ideogram 4.5 Precise Edit
Ideogram 4.5 Precise Edit works on an existing image rather than starting from an empty canvas.
Image $0.072
Image
Krea 3
Krea 3 creates images from a description and supports changes to selected parts of a scene.
Image $0.031
Image
Seedream 5.5
Seedream 5.5 is ByteDance’s model for creating and changing images.
Image $0.024
Image
Recraft V4
Design-focused image generation with precise style control
Image $0.04
Video
HeyGen Video Translate 1.0
HeyGen Video Translate translates speech in an existing video.
5 s clip from $0.081$0.02 / sec
Video
Kling VIDEO 4.0
Kling VIDEO 4.0 generates clips from text and images and supports video-reference and editing workflows.
5 s clip from $0.94$0.19 / sec
Video
Kling VIDEO 4.0 Flash
Kling VIDEO 4.0 Flash is a distinct Kling variant for generating and revising video scenes.
5 s clip from $0.56$0.11 / sec
Video
Seedance 2.5 Flash
Seedance 2.5 Flash is ByteDance’s distinct model for creating clips and working with source media.
5 s clip from $0.44$0.09 / sec
Video
ByteDance Seedance 2.0 Mini
Compact Seedance 2.0 variant for faster, lighter multimodal video generation — T2V, I2V, V2V, synced audio
5 s clip from $0.44$0.09 / sec
Video
FLUX 3 Video
Black Forest Labs multimodal video model with synced audio: 5-20s clips across text, image and video-to-video
5 s clip from $1.03$0.21 / sec
Video
FLUX Video Upscale
Black Forest Labs video upscaler to 1080p, 2K or 4K: clips up to 20s and 50 MB, 1.5x-3x, precise and creative modes
from $0.09 / sec at 1024×1024 output
Video
Gemini Omni Flash 1.2
Gemini Omni Flash 1.2 is Google’s model for creating and revising short clips.
6 s clip from $0.14from $0.024 / sec
Video
Grok Imagine Video
xAI video model with native synced audio: text, image or video to video, 480p or 720p, up to 15 seconds
6 s clip from $0.36$0.06 / sec
Video
Grok Imagine Video 1.5 Lite
Faster, lower-cost Grok Imagine Video 1.5: text-to-video and image-to-video at 480p/720p/1080p, 1-15s clips with native audio
6 s clip from $0.14$0.02 / sec
Video
HeyGen Avatar IV
Lifelike talking avatars from a single photo, driven by text or your own audio
from $0.0462 / sec
Video
Kling VIDEO 3.0 Pro
Pro tier of Kling 3.0: 1080p with audio, motion sync and consistent characters
5 s clip from $0.67$0.13 / sec
Video
Kling VIDEO 3.0 Standard
Affordable tier of Kling 3.0: 1080p with audio and motion sync
5 s clip from $0.50$0.1 / sec
Video
Kling VIDEO O3 Pro
Kling flagship video model: 1080p, first and last frame control, image-to-video
5 s clip from $0.67$0.13 / sec
Video
Kling VIDEO O3 Standard
Standard tier of Kling O3: the balance of quality and price
5 s clip from $0.50$0.1 / sec
Video
MiniMax H3
MiniMax multimodal video model with native synced audio: 5-15s clips up to 1440p from text, images, video and audio
5 s clip from $0.48$0.1 / sec
Video
MiniMax H3 Fast
Fast, low-cost MiniMax H3 tier: 480p clips of 4-15s with sound from text, first/last frames, up to 9 reference images or 3 reference videos
5 s clip from $0.28$0.06 / sec
Video
MiniMax H3 Max
MiniMax high-throughput video model: text-to-video and image-to-video up to 15s with native synced audio and first/last frame control
5 s clip from $0.30$0.06 / sec
Video
MiniMax H3 Max Turbo
Faster MiniMax H3 Max tier: 480p/768p clips of 5-15s with sound from text or first/last frames
5 s clip from $0.15$0.03 / sec
Video
Seedance 2.0
ByteDance multimodal video model with synced audio: multi-shot clips up to 15s from text, images, video and audio
5 s clip from $0.88from $0.1752 / sec without a video reference
Video
Seedance 2.5
ByteDance production-grade video model: native 30-second clips, large reference sets and precise localized edits
5 s clip from $0.67$0.13 / sec
Video
SkyReels V4
One video model for text, image and video input, edit and extend: up to 1080p, 32 fps, 15-second clips with synced sound
5 s clip from $0.66$0.13 / sec
Video
Veo 3.1
Google cinematic video model with native audio, image-to-video, video-to-video and 4K
8 s clip from $1.92from $0.24 / sec without audio
Video
Veo 3.1 Fast
Faster Veo 3.1: quick turnaround, 1080p or 4K with audio
8 s clip from $0.96from $0.12 / sec without audio
Video
Wan3.0 Prime
Faster-inference version of Alibaba Wan3.0: same multimodal workflows and output quality, lower latency
5 s clip from $0.48$0.1 / sec
Video
Wan3.0 Video
Alibaba multimodal video model: clips up to 30s with native audio, 10 reference images, video and audio references, editing and extension
5 s clip from $0.35$0.07 / sec
3D
3D Model Generator
Create a 3D object from text or reference views. Download the GLB and inspect geometry, textures and materials in your own application.
Gen: $0.36
Sound
Fish Audio Drama 3
Fish Audio Drama 3: directed voice performances with plain-language directions in square brackets, two-voice dialogue
$0.012 / 1K chars A minute of speech ≈ $0.01
Sound
HeyGen Voice Turbo
Faster, lower-cost HeyGen Voice with the same 10 voices
$0.0048 / 1K chars A minute of speech ≈ $0.0041
Sound
HeyGen Voice
HeyGen text-to-speech: 10 ready voices for videos, presentations and avatars
$0.018 / 1K chars A minute of speech ≈ $0.015
Sound
ElevenLabs Turbo v2
Fast English-only ElevenLabs model
$0.048 / 1K chars A minute of speech ≈ $0.041
Sound
ElevenLabs Turbo v2.5
Low-latency ElevenLabs model balancing quality and speed, 32 languages
$0.048 / 1K chars A minute of speech ≈ $0.041
Sound
ElevenLabs Flash v2.5
Ultra-low-latency ElevenLabs model for conversational use, 32 languages
$0.048 / 1K chars A minute of speech ≈ $0.041
Sound
ElevenLabs Multilingual v2
Consistent ElevenLabs narration for long-form voice-overs and audiobooks, 29 languages
$0.096 / 1K chars A minute of speech ≈ $0.082
Sound
ElevenLabs Eleven v3
Emotionally rich ElevenLabs speech with inline audio tags, 70+ languages
$0.096 / 1K chars A minute of speech ≈ $0.082
Sound
ElevenLabs Eleven v4 Turbo
Faster Eleven v4: same expressive delivery and audio tags, 90+ languages
$0.048 / 1K chars A minute of speech ≈ $0.041
Sound
ElevenLabs Eleven v4
ElevenLabs' most expressive model: emotion and delivery via inline audio tags, 90+ languages
$0.096 / 1K chars A minute of speech ≈ $0.082
Sound
Fish Audio S2.1 Pro
Expressive speech you direct inside the text: emotions, pauses, two-voice dialogue; 80+ languages and voice cloning
$0.018 / 1K chars A minute of speech ≈ $0.015
Sound
Seed Audio 1.0
Generate audio from a written direction: a spoken line, voice delivery and sound mood. Audition the example and refine your own brief.
$0.1896 / min
Sound
MiniMax Music 2.6
Full songs with vocals from your lyrics or a description, plus instrumental tracks
$0.18 / track
Sound
xAI TTS
Lively text-to-speech with intonation tags for pauses, whispers and laughter: 27 voices, 20 languages
$0.018 / 1K chars A minute of speech ≈ $0.015
Sound
MiniMax Speech 2.8
Studio-quality speech with 142 voices across many languages; Turbo mode is faster and cheaper
$0.12 / 1K chars A minute of speech ≈ $0.10
Sound
AssemblyAI TTS 1
AssemblyAI TTS 1 reads text aloud with preset voices.
$0.018 / 1K chars A minute of speech ≈ $0.015
Sound
Google Gemini 3.8 Flash Lite TTS
Gemini 3.8 Flash Lite TTS is Google’s speech model in the Gemini TTS family.
$0.0108 / min
Sound
Google Gemini 3.8 Flash TTS
Gemini 3.8 Flash TTS is Google’s model for reading prepared text aloud.
$0.0162 / min
Sound
Inworld Realtime TTS-2
Inworld Realtime TTS-2 generates speech from text using a selected preset voice.
$0.042 / 1K chars A minute of speech ≈ $0.036
Sound
Microsoft MAI-Voice 2.1
Microsoft MAI-Voice 2.1 reads prepared narration, explanations and other text aloud.
$0.0264 / 1K chars A minute of speech ≈ $0.022
Sound
Microsoft MAI-Voice 2.1 Flash
Microsoft MAI-Voice 2.1 Flash converts text to speech using preset voices.
$0.018 / 1K chars A minute of speech ≈ $0.015
Sound
Mistral Voxtral TTS 3
Mistral Voxtral TTS 3 turns text into speech and accepts emotion and pacing cues in the text.
$0.0156 / 1K chars A minute of speech ≈ $0.013
All models with prices

The next frame is yours.

Free: 3 images per day after signing in with Google or Telegram. No card required.

Model

Prompt

Make one like it