Qwen3-Coder 480B-A35B Instruct vs Mistral Medium 3: API price and specs

Qwen3-Coder 480B-A35B Instruct is 45% cheaper than Mistral Medium 3 on input price.

Qwen3-Coder 480B-A35B Instruct is 60% cheaper than Mistral Medium 3 on output price.

Qwen3-Coder 480B-A35B Instruct is 52% cheaper than Mistral Medium 3 on a 1M-in / 200k-out workload.

Field	Qwen3-Coder 480B-A35B Instruct	Mistral Medium 3
Lowest input, per 1M	$0.22	$0.40 +81.8%
Median input, per 1M	$0.36	$0.40 +10.7%
Lowest output, per 1M	$0.80	$2.00 +150%
Median output, per 1M	$1.58	$2.00 +27%
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.38	$0.80 +110.5%
Context	262K	262K
Max output	262K	105K +60%
Providers	23	5 +78.3%
Regions	EU, US	EU, GLOBAL
Accepts	audio, image, text, video	file, image, text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	google-vertex	edenai

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, edenai, google-vertex, kilo, openrouter

Frequently asked questions

Which is cheaper, Qwen3-Coder 480B-A35B Instruct or Mistral Medium 3?

Qwen3-Coder 480B-A35B Instruct is 45% cheaper than Mistral Medium 3 on input price. Qwen3-Coder 480B-A35B Instruct is 60% cheaper than Mistral Medium 3 on output price. Qwen3-Coder 480B-A35B Instruct is 52% cheaper than Mistral Medium 3 on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3-Coder 480B-A35B Instruct or Mistral Medium 3?

Qwen3-Coder 480B-A35B Instruct: 262K tokens; Mistral Medium 3: 262K tokens.

Where can I use both Qwen3-Coder 480B-A35B Instruct and Mistral Medium 3?

aiml, edenai, google-vertex, kilo, openrouter