Decision support
Ling 3.0 Flash VL vs Ternary Bonsai 2 9B
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
September 4, 2026
October 16, 2026
Context window
131K
262K
Native context
—
—
Max output tokens
32,768
65,536
Knowledge cutoff
—
—
Open weights
Open weights
Open weights
Parameter count
125B
9B
API pricing · USD per 1M tokens
Input
$0.06
$0.08
Output
$0.18
$0.13
Cached input
$0.012
$0.04
Cache write
—
—
Capabilities and modalities
Input modalities
text, image, video
text, image
Output modalities
text
text
Tool calling
Supported
Supported
Reasoning option
Supported
Supported
Supported options
frequency_penalty, include_reasoning, logit_bias, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p
frequency_penalty, include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
Capabilities
—
—
Architecture and availability
Architecture
—
—
Model families
—
—
Tokenizer
Other
Qwen
Instruction format
—
—
License
MIT
—
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.