Decision support
ERNIE 4.5 VL 424B A47B vs Qwen3 Coder 480B A35B
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 30, 2025
July 22, 2025
Context window
123K
262K
Native context
—
256K
Max output tokens
16,000
65,536
Knowledge cutoff
2025-03-31
2025-06-30
Open weights
Open weights
Open weights
Parameter count
424B
30B
API pricing · USD per 1M tokens
Input
$0.42
$0.30
Output
$1.25
$1.00
Cached input
—
$0.10
Cache write
—
—
Capabilities and modalities
Input modalities
image, text
text
Output modalities
text
text
Tool calling
—
Supported
Reasoning option
Supported
—
Supported options
frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, repetition_penalty, seed, stop, temperature, top_k, top_p
frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p
Capabilities
—
—
Architecture and availability
Architecture
—
—
Model families
—
—
Tokenizer
Other
Qwen3
Instruction format
—
—
License
Apache 2.0
—
Providers
0
2
Provider endpoints
0
2
Ollama variants
0
0
Metadata source
ai-research
ai-research
A dash means the field is not reported. Provider-specific performance and pricing may differ.