Decision support
HappyHorse 1.1 vs Ray3.2
Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.
Ray3.2
Luma AI
Benchmark results
No benchmark results have been matched to these models yet.
Model specifications
Release date
June 22, 2026
June 9, 2026
Context window
—
—
Native context
—
—
Max output tokens
0
—
Knowledge cutoff
—
—
Open weights
Unknown
Closed
Parameter count
—
—
API pricing · USD per 1M tokens
Input
$0.00
—
Output
$0.00
—
Cached input
—
—
Cache write
—
—
Capabilities and modalities
Input modalities
text, image
text, image, video
Output modalities
video
video
Tool calling
—
—
Reasoning option
—
—
Supported options
max_tokens, presence_penalty, response_format, seed, temperature, top_p
—
Capabilities
—
—
Architecture and availability
Architecture
—
—
Model families
—
—
Tokenizer
Other
—
Instruction format
—
—
License
—
proprietary
Providers
1
0
Provider endpoints
1
0
Ollama variants
0
0
Metadata source
ai-research
curated
A dash means the field is not reported. Provider-specific performance and pricing may differ.