AI Rate Card

Qwen3.5 397B-A17B vs Mistral Small 3: API price and specs

Mistral Small 3 is 70% cheaper than Qwen3.5 397B-A17B on input price.

Mistral Small 3 is 92% cheaper than Qwen3.5 397B-A17B on output price.

Mistral Small 3 is 82% cheaper than Qwen3.5 397B-A17B on a 1M-in / 200k-out workload.

Qwen3.5 397B-A17B has a 104.8% larger context than Mistral Small 3.

FieldQwen3.5 397B-A17BMistral Small 3
Lowest input, per 1M$0.16 +228.8%$0.05
Median input, per 1M$0.55 +1000%$0.05
Lowest output, per 1M$0.99 +1133%$0.08
Median output, per 1M$3.60 +4400%$0.08
Lowest unit price——
Cost of 1M in + 200k out$0.36 +448%$0.066
Context262K128K +51.2%
Max output262K16K +93.8%
Providers307 +76.7%
RegionsCH, EU, GLOBAL, USEU, US
Acceptsfile, 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-msvideoimage, text
Returnstexttext
TypeText modelsText models
Free optionnono
Cheapest provideraihubmixdeepinfra

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

deepinfra, edenai, fastrouter, kilo, openrouter, poe, trustedrouter

Frequently asked questions

Which is cheaper, Qwen3.5 397B-A17B or Mistral Small 3?

Mistral Small 3 is 70% cheaper than Qwen3.5 397B-A17B on input price. Mistral Small 3 is 92% cheaper than Qwen3.5 397B-A17B on output price. Mistral Small 3 is 82% cheaper than Qwen3.5 397B-A17B on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3.5 397B-A17B or Mistral Small 3?

Qwen3.5 397B-A17B: 262K tokens; Mistral Small 3: 128K tokens.

Where can I use both Qwen3.5 397B-A17B and Mistral Small 3?

deepinfra, edenai, fastrouter, kilo, openrouter, poe, trustedrouter