AI Rate Card

Qwen3.6 35B-A3B vs Codestral 25.08: API price and specs

Qwen3.6 35B-A3B is 96% cheaper than Codestral 25.08 on input price.

Qwen3.6 35B-A3B is 90% cheaper than Codestral 25.08 on output price.

Qwen3.6 35B-A3B is 94% cheaper than Codestral 25.08 on a 1M-in / 200k-out workload.

Qwen3.6 35B-A3B has a 2.4% larger context than Codestral 25.08.

FieldQwen3.6 35B-A3BCodestral 25.08
Lowest input, per 1M$0.012$0.30 +2400%
Median input, per 1M$0.17$0.32 +87.2%
Lowest output, per 1M$0.09$0.90 +900%
Median output, per 1M$1.01 +6.1%$0.95
Lowest unit price——
Cost of 1M in + 200k out$0.03$0.48 +1500%
Context262K256K +2.3%
Max output262K256K +2.3%
Providers276 +77.8%
RegionsEU, GLOBAL, TW, USEU, GLOBAL
Acceptsaudio, image, image/bmp, image/heic, image/jpeg, image/png, image/tiff, image/webp, text, video, video/mp4, video/quicktime, video/x-flv, video/x-matroska, video/x-ms-wmv, video/x-msvideofile, text
Returnstexttext
TypeText modelsText models
Free optionnono
Cheapest providerinferxedenai

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 35B-A3B or Codestral 25.08?

Qwen3.6 35B-A3B is 96% cheaper than Codestral 25.08 on input price. Qwen3.6 35B-A3B is 90% cheaper than Codestral 25.08 on output price. Qwen3.6 35B-A3B is 94% cheaper than Codestral 25.08 on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3.6 35B-A3B or Codestral 25.08?

Qwen3.6 35B-A3B: 262K tokens; Codestral 25.08: 256K tokens.

Where can I use both Qwen3.6 35B-A3B and Codestral 25.08?

aiml, cortecs, edenai, kilo, openrouter, trustedrouter