MixtrainDocsBlog

External Models

Mixtrain integrates with leading AI model providers for image generation, video generation, and multimodal tasks. Add a provider once, and all its models become available across your workflows, evaluations, and routers.

Supported Providers

Image & Video Generation

ProviderModelsDescription
RunwayGen-4.5, GWM-1Video generation and world models
Luma LabsRay3.14, Ray3 ModifyVideo, 3D, and HDR generation
Black Forest LabsFLUX.2 Pro, FLUX.2 [klein]High-quality image generation and editing
falFLUX.2, Kling 2.6, LTX 2.01000+ image, video, and audio models
GoogleVeo 3.1, GenieVideo generation and interactive 3D worlds

Language & Multimodal

ProviderModelsDescription
GoogleGemini 3.1 Pro, Gemini 3 Deep ThinkMultimodal reasoning and agentic AI
AnthropicClaude Opus 4.6, Sonnet 4.6Advanced reasoning and coding
OpenAIGPT-5.4, GPT-5 miniLanguage and image models

Quick Start

Add a provider and start generating videos in a few lines:

mixtrain provider add runway
from mixtrain import Model

model = Model("gen-4.5")
result = model.run({
    "prompt": "A drone shot flying over a mountain lake at sunrise",
    "duration": 4
})

How It Works

  1. Add a provider with your API key using the CLI or SDK.
  2. Browse available models with mixtrain model catalog.
  3. Use models anywhere in Mixtrain — workflows, evaluations, routers, or direct calls.

External models work seamlessly alongside your own fine-tuned models, so you can mix and match providers in a single workflow or router.

See Also

On this page