Decision support
Elephant 1 vs Clef Flash
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
October 21, 2026
October 1, 2026
Context window
16K
25K
Native context
—
256K
Max output tokens
14,745
22,118
Knowledge cutoff
—
—
Open weights
Open weights
Open weights
Parameter count
9.4B
9B
API pricing · USD per 1M tokens
Input
$0.035
$0.019
Output
$0.00
$0.00
Cached input
—
—
Cache write
—
—
Capabilities and modalities
Input modalities
text, image
text, image
Output modalities
decisions
decisions
Tool calling
—
—
Reasoning option
—
—
Supported options
—
temperature
Capabilities
—
—
Architecture and availability
Architecture
—
—
Model families
—
—
Tokenizer
Other
Qwen
Instruction format
—
—
License
—
Apache-2.0
Providers
1
3
Provider endpoints
1
3
Ollama variants
0
4
Metadata source
ai-research
ai-research
A dash means the field is not reported. Provider-specific performance and pricing may differ.