Qwen3-Coder 480B-A35B Instruct vs ERNIE 4.5 VL 424B A47B: API price and specs

Qwen3-Coder 480B-A35B Instruct is 48% cheaper than ERNIE 4.5 VL 424B A47B on input price.

Qwen3-Coder 480B-A35B Instruct is 36% cheaper than ERNIE 4.5 VL 424B A47B on output price.

Qwen3-Coder 480B-A35B Instruct is 43% cheaper than ERNIE 4.5 VL 424B A47B on a 1M-in / 200k-out workload.

Qwen3-Coder 480B-A35B Instruct has a 113.1% larger context than ERNIE 4.5 VL 424B A47B.

Field	Qwen3-Coder 480B-A35B Instruct	ERNIE 4.5 VL 424B A47B
Lowest input, per 1M	$0.22	$0.42 +90.9%
Median input, per 1M	$0.36	$0.42 +16.2%
Lowest output, per 1M	$0.80	$1.25 +56.2%
Median output, per 1M	$1.58 +26%	$1.25
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.38	$0.67 +76.3%
Context	262K	123K +53.1%
Max output	262K	16K +93.9%
Providers	23	3 +87%
Regions	EU, US	—
Accepts	audio, image, text, video	image, text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	google-vertex	jiekou

Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.

Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.

Providers selling both

aiml, jiekou, kilo

Frequently asked questions

Which is cheaper, Qwen3-Coder 480B-A35B Instruct or ERNIE 4.5 VL 424B A47B?

Qwen3-Coder 480B-A35B Instruct is 48% cheaper than ERNIE 4.5 VL 424B A47B on input price. Qwen3-Coder 480B-A35B Instruct is 36% cheaper than ERNIE 4.5 VL 424B A47B on output price. Qwen3-Coder 480B-A35B Instruct is 43% cheaper than ERNIE 4.5 VL 424B A47B on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3-Coder 480B-A35B Instruct or ERNIE 4.5 VL 424B A47B?

Qwen3-Coder 480B-A35B Instruct: 262K tokens; ERNIE 4.5 VL 424B A47B: 123K tokens.

Where can I use both Qwen3-Coder 480B-A35B Instruct and ERNIE 4.5 VL 424B A47B?

aiml, jiekou, kilo