Decision support
North Mini Code vs Kimi K2.7 Code Highspeed
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
June 17, 2026
June 12, 2026
Context window
256K
262K
Native context
488K
—
Max output tokens
64,000
262,144
Knowledge cutoff
2025-09-23
2025-01
Open weights
Open weights
Open weights
Parameter count
30.5B
—
API pricing · USD per 1M tokens
Input
$0.00
—
Output
$0.00
—
Cached input
—
—
Cache write
—
—
Capabilities and modalities
Input modalities
text
text, image, video
Output modalities
text
text
Tool calling
Supported
Supported
Reasoning option
Supported
Supported
Supported options
frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, seed, stop, temperature, tool_choice, tools, top_k, top_p
tools, structured_outputs, reasoning
Capabilities
—
—
Architecture and availability
Architecture
—
—
Model families
—
—
Tokenizer
Cohere
—
Instruction format
—
—
License
—
—
Providers
0
0
Provider endpoints
0
0
Ollama variants
6
0
Metadata source
ai-research
ai-research
A dash means the field is not reported. Provider-specific performance and pricing may differ.