CLEAR PRICING

What you need. What you use.

Explore current GPU and model API rates. Prices are retrieved from the platform and displayed in USD.

01 / GPU CLOUD

GPU Cloud

GPU CLOUD — USD
GPU model	GPU memory	Hourly rate	Get started
RTX Pro 6000	96 GB	$1.89 / hour	Get started

All prices are in USD. Check the console for final charges.

02 / MODEL API

Model API

Compare input, output, and cache rates per 1M tokens. Video models have a separate resolution-based table with their billing units below.

Language

USD per 1M tokens

Language — USD per 1M tokens
Model	Input	Output	Cache read
DeepSeek-V4-Flash	$0.49	$1.42	$0.05
DeepSeek-V4-Pro	$0.91	$2.72	$0.1
GLM-5.2	$1	$3	$0.2
GLM-5.3	$1.25	$4.3	$0.2
gpt-oss-20bContext length: 128,000 tokens	$0.05	$0.2	$0.025
Kimi-K3	$2	$12	$0.2
Llama-3.1-8B-InstructContext length: 128,000 tokens	$0.1	$0.1	$0.05
MiniMax-M3	$0.2	$0.9	$0.05
qwen3.8-flash	$0.0935	$0.374	$0.01866
qwen3.8-max	$1.9	$5.7	$0.2

Vision

USD per 1M tokens

Vision — USD per 1M tokens
Model	Input	Output	Cache read
Qwen3.8-27BContext length: 32,768 tokens	$0.3	$0.6	$0.15

Embedding

USD per 1M tokens

Embedding — USD per 1M tokens
Model	Input	Output
Jina-Embeddings-V3	$0.02	—
Jina-Embeddings-V4	$0.12	—
qwen3-embedding-0.6b	$0.12	—

Reranking

USD per 1M tokens

Reranking — USD per 1M tokens
Model	Input	Output
BGE-Reranker-V2-M3	$0.03	—

Image

USD per 1M tokens

Image — USD per 1M tokens
Model	Input	Output
Qwen-Image	—	$30
Z-Image-Turbo	—	$10

Transcription

USD per 1M tokens

Transcription — USD per 1M tokens
Model	Input	Output
Fun-ASR-Nano	$0.05	—
Qwen3-ASR-1.7B	$0.05	—
Whisper-Large-V3-Turbo	$0.1	—

Text-to-speech

USD per 1M tokens

Text-to-speech — USD per 1M tokens
Model	Input	Output
Kokoro-82M	—	$1
Qwen3-TTS	—	$2

Voice cloning

USD per 1M tokens

Voice cloning — USD per 1M tokens
Model	Input	Output	Cache read
ViiTorVoice-NAR	$0.1	$0.5	$0.05

Diarization

USD per 1M tokens

Diarization — USD per 1M tokens
Model	Input	Output
pyannote Speaker Diarization 3.1	$4	—

Audio

USD per 1M tokens

Audio — USD per 1M tokens
Model	Input	Output
Stable Audio Open 1.0	—	$8

Video generation pricing

Rates depend on output resolution and reference video input. Check the billing unit for each model.

Seedance 2.0

Seedance 2.0 — Video generation pricing
Resolution	Reference video	Rate
480p / 720p	Without video	$7.14 / 1M tokens
480p / 720p	With video	$4.39 / 1M tokens
1080p	Without video	$7.85 / 1M tokens
1080p	With video	$4.79 / 1M tokens
4k	Without video	$4.08 / 1M tokens
4k	With video	$2.45 / 1M tokens

Wan2.2-T2V-A14B

Wan2.2-T2V-A14B — Video generation pricing
Resolution	Reference video	Rate
480p	Without video	$0.05 / sec
480p	With video	$0.05 / sec
720p	Without video	$0.08 / sec
720p	With video	$0.08 / sec

Wan2.2-S2V-14B (Presenter / Talking Head)

Wan2.2-S2V-14B (Presenter / Talking Head) — Video generation pricing
Resolution	Reference video	Rate
480p	Without video	$0.05 / sec
480p	With video	$0.05 / sec
720p	Without video	$0.08 / sec
720p	With video	$0.08 / sec

LTX 2.5

LTX 2.5 — Video generation pricing
Resolution	Reference video	Rate
480p	Without video	$0.05 / sec
480p	With video	$0.05 / sec
720p	Without video	$0.05 / sec
720p	With video	$0.05 / sec
1080p	Without video	$0.08 / sec
1080p	With video	$0.08 / sec

Wan 3.0

Wan 3.0 — Video generation pricing
Resolution	Reference video	Rate
480p	Without video	$0.055 / sec
480p	With video	$0.055 / sec
720p	Without video	$0.11 / sec
720p	With video	$0.11 / sec
1080p	Without video	$0.22 / sec
1080p	With video	$0.22 / sec

wan3.0-video-prime

wan3.0-video-prime — Video generation pricing
Resolution	Reference video	Rate
480p	Without video	$0.0748 / sec
480p	With video	$0.0748 / sec
720p	Without video	$0.154 / sec
720p	With video	$0.154 / sec
1080p	Without video	$0.308 / sec
1080p	With video	$0.308 / sec

Seedance 2.5

Seedance 2.5 — Video generation pricing
Resolution	Reference video	Rate
480p / 720p	Without video	$10.914 / 1M tokens
480p / 720p	With video	$6.528 / 1M tokens
1080p	Without video	$11.934 / 1M tokens
1080p	With video	$7.14 / 1M tokens
4k	Without video	$4 / 1M tokens
4k	With video	$2.4 / 1M tokens

Public platform rates refresh every five minutes. A dash means a rate is not provided; it does not mean free. Check the console for final charges.

GOOD TO KNOW

A few things before you start.

What is the difference between GPU Cloud and Model API?

GPU Cloud gives you dedicated GPU resources to run your own models and software. Model API lets you call available models without managing infrastructure. Choose either, or use both to suit your workload.

Can I use my existing OpenAI SDK?

Yes. We provide an OpenAI-compatible endpoint. Configure the API URL, your API key, and the model ID. Check the developer documentation for each model’s supported capabilities and request format.

Where can I find pricing?

The pricing page shows current GPU and model API rates. Check the console for final charges and available configurations. Prices are displayed in USD.

Can I launch a GPU on this website?

This is the official website for exploring products and models. GPU launch, API key creation, billing, and account management are available in the console.

COMPUTE WITHOUT BOUNDARIES

Your next AI. Starts with GIGACOMMA.

Start something bigger with the compute you need.

Open GPU console Get an API key