SkiaSKIA

Supported Models

Last updated February 26, 2026

Google AI Studio

Google's AI platform offering Gemini LLMs and Veo video generation.

Gemini Pro

LLM

Advanced reasoning and multimodal understanding with 1M token context.

1000K contextPer-token pricing via Google AI Studio

Gemini Flash

LLM

Fast, cost-efficient model for everyday tasks.

1000K contextPer-token pricing via Google AI Studio

Nano Banana Pro

Image

High-quality image generation via Google AI Studio.

1024x1024Per-image pricing

Veo 3.1

Video

State-of-the-art video generation with audio. Supports text-to-video and image-to-video.

1080pPer-second pricing

OpenAI

OpenAI's platform with GPT models and Sora video generation.

GPT-5.2

LLM

Advanced LLM with 128K context window.

128K contextPer-token pricing via OpenAI

Sora 2

Video

High-quality video generation from text and image inputs.

1080pPer-second pricing

DeepSeek

Cost-efficient open-source LLM with strong reasoning capabilities.

DeepSeek V3.2

LLM

High-performance text-only LLM with 128K context.

128K contextPer-token pricing via DeepSeek API

Black Forest Labs

Creators of the FLUX family of image generation models.

FLUX.2 Pro

Image

High-quality image generation with excellent prompt adherence.

2048x2048Per-image via BFL API

fal.ai

Fast inference platform hosting Kling, Wan, Seedance, and more.

Kling 3.0

Video

High-quality video generation with strong motion consistency.

1080pPer-second via fal.ai

Seedance 1.5 Pro

Video

Dance and motion-focused video generation.

1080pPer-second via fal.ai

Wan 2.2

Video

Text-to-video with strong character consistency.

1080pPer-second via fal.ai

Wan 2.6

Video

Latest Wan model with improved quality and longer durations.

1080pPer-second via fal.ai

HunyuanVideo

Video

Tencent's video generation model via fal.ai.

1080pPer-second via fal.ai

ElevenLabs

Industry-leading voice cloning and text-to-speech.

Voice Cloning

Voice

Clone any voice from a short audio sample. Use for character dialogue.

Per-character pricing via ElevenLabs

Text-to-Speech

Voice

High-quality speech synthesis with cloned or preset voices.

Per-character pricing via ElevenLabs

Local Models

Run models on your Mac. No API key needed. Zero per-generation cost.

FLUX.2 klein

Image

Lightweight FLUX model for local image generation on Mac (Metal/MPS).

1024x1024Free (runs locally)

Wan 2.6 T2V

Video

Text-to-video on device. Requires 16GB+ RAM.

720pFree (runs locally)

Qwen3-4B

LLM

Compact LLM via Ollama for script writing and AI assistant. Runs locally.

32K contextFree (runs locally via Ollama)

Start creating with these models.

Join the waitlist for early access and founding member pricing.

We'll email you when Skia is ready. No spam. Unsubscribe anytime.