Models & Pricing
Pay-as-you-go. No monthly commitment — top up anytime (€5–€200). Every model self-hosted on dedicated GPUs in Greece.
Qwen3-Coder 30B AWQ
~16 GB
Static
Premium coding LLM — demand driver, always loaded
Flux.1-Schnell FP8
~5 GB
Dynamic
Text-to-image generation, fast throughput
Whisper Large v3 ★
~3 GB
Dynamic
Transcription PRIMARY — Greek premium & general
BGE-M3 + nomic-embed
~2 GB
Static
Semantic embeddings, RAG pipelines
XTTS-v2
~1 GB
Dynamic
Text-to-speech with voice cloning
KV Cache — ~5 GB — LLM context buffer (not a billable model)
SDXL Turbo FP8
~3 GB
Static
Ultra-fast image gen — always loaded
Wan2.1-1.3B T2V / I2V
~8 GB
Dynamic
Budget video 480p — ~15 clips/hr
Wan2.1-14B INT4
~13 GB
Dynamic
Premium video broadcast quality
Mistral 7B AWQ
~5 GB
Static
General purpose LLM, agents
Qwen3-8B
~6 GB
Static
Agent / coding LLM
Subscription Plans
Monthly plans with pre-allocated credits for higher volume. All plans include full API access.
Starter
€9.99 /mo
12,000 credits
Ideal for individual developers and small projects.
Popular
Pro
€24.99 /mo
40,000 credits
For professional developers and growing teams.
Business
€69.99 /mo
150,000 credits
Full platform access for businesses. Priority support.
API Endpoint
Base URL
https://api.mastera-ai.com
Full website coming soon.
In the meantime, explore our API at the endpoint above.