Decision support
Ink 2 vs GPT-Realtime-2.1
Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.
Ink 2
Cartesia
Benchmark results
No benchmark results have been matched to these models yet.
Model specifications
Release date
June 15, 2026
July 6, 2026
Context window
—
128K
Native context
—
—
Max output tokens
—
32,000
Knowledge cutoff
—
2024-09-30
Open weights
Closed
Closed
Parameter count
—
—
API pricing · USD per 1M tokens
Input
—
—
Output
—
—
Cached input
—
—
Cache write
—
—
Capabilities and modalities
Input modalities
audio
text, audio, image
Output modalities
text
text, audio
Tool calling
—
Supported
Reasoning option
—
Supported
Supported options
—
tools, reasoning
Capabilities
—
—
Architecture and availability
Architecture
—
—
Model families
—
—
Tokenizer
—
—
Instruction format
—
—
License
proprietary
—
Providers
0
0
Provider endpoints
0
0
Ollama variants
0
0
Metadata source
curated
ai-research
A dash means the field is not reported. Provider-specific performance and pricing may differ.