Decision support
rerank-2.5-lite vs Qwen3 Reranker 0.6B
Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.
Benchmark results
No benchmark results have been matched to these models yet.
Model specifications
Release date
July 27, 2026
August 26, 2026
Context window
32K
33K
Native context
—
—
Max output tokens
28,800
0
Knowledge cutoff
—
—
Open weights
Unknown
Open weights
Parameter count
—
0.6B
API pricing · USD per 1M tokens
Input
$0.00
$0.00
Output
$0.00
$0.00
Cached input
—
—
Cache write
—
—
Capabilities and modalities
Input modalities
text
text
Output modalities
rerank
rerank
Tool calling
—
—
Reasoning option
—
—
Supported options
—
—
Capabilities
—
—
Architecture and availability
Architecture
—
—
Model families
—
—
Tokenizer
Other
Qwen3
Instruction format
—
—
License
—
—
Providers
1
1
Provider endpoints
1
1
Ollama variants
0
0
Metadata source
ai-research
openrouter
A dash means the field is not reported. Provider-specific performance and pricing may differ.