Qwen3.6 27B vs Codestral 25.08: API price and specs

Qwen3.6 27B is 92% cheaper than Codestral 25.08 on input price.

Qwen3.6 27B is 69% cheaper than Codestral 25.08 on output price.

Qwen3.6 27B is 83% cheaper than Codestral 25.08 on a 1M-in / 200k-out workload.

Qwen3.6 27B has a 2.4% larger context than Codestral 25.08.

Field	Qwen3.6 27B	Codestral 25.08
Lowest input, per 1M	$0.025	$0.30 +1100%
Median input, per 1M	$0.40 +26.8%	$0.32
Lowest output, per 1M	$0.28	$0.90 +221.4%
Median output, per 1M	$3.19 +236%	$0.95
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.081	$0.48 +492.6%
Context	262K	256K +2.3%
Max output	262K	256K +2.3%
Providers	27	6 +77.8%
Regions	EU, GLOBAL, US	EU, GLOBAL
Accepts	application/pdf, audio, file, image, image/bmp, image/gif, image/heic, image/jpeg, image/png, image/tiff, image/webp, pdf, text, video, video/mp4, video/quicktime, video/webm	file, text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	inferx	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, cortecs, edenai, kilo, openrouter, trustedrouter

Frequently asked questions

Which is cheaper, Qwen3.6 27B or Codestral 25.08?

Qwen3.6 27B is 92% cheaper than Codestral 25.08 on input price. Qwen3.6 27B is 69% cheaper than Codestral 25.08 on output price. Qwen3.6 27B is 83% cheaper than Codestral 25.08 on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3.6 27B or Codestral 25.08?

Qwen3.6 27B: 262K tokens; Codestral 25.08: 256K tokens.

Where can I use both Qwen3.6 27B and Codestral 25.08?

aiml, cortecs, edenai, kilo, openrouter, trustedrouter