Decision support
Aion-3.0-Mini vs Composer 2.5
Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.
Composer 2.5
Cursor
Benchmark results
No benchmark results have been matched to these models yet.
Model specifications
Release date
July 7, 2026
May 18, 2026
Context window
131K
—
Native context
—
—
Max output tokens
32,768
—
Knowledge cutoff
—
—
Open weights
Closed
Closed
Parameter count
—
—
API pricing · USD per 1M tokens
Input
$0.70
$0.50
Output
$1.40
$2.50
Cached input
$0.18
—
Cache write
—
—
Capabilities and modalities
Input modalities
text
text
Output modalities
text
text
Tool calling
Supported
—
Reasoning option
Supported
—
Supported options
include_reasoning, max_tokens, reasoning, response_format, temperature, tool_choice, tools, 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.