AI Rate Card

Qwen3.5 397B-A17B vs Sao10K Stheno 8b: API price and specs

Sao10K Stheno 8b is 70% cheaper than Qwen3.5 397B-A17B on input price.

Sao10K Stheno 8b is 95% cheaper than Qwen3.5 397B-A17B on output price.

Sao10K Stheno 8b is 83% cheaper than Qwen3.5 397B-A17B on a 1M-in / 200k-out workload.

Qwen3.5 397B-A17B has a 3100% larger context than Sao10K Stheno 8b.

FieldQwen3.5 397B-A17BSao10K Stheno 8b
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 +1872.8%$0.05
Median output, per 1M$3.60 +7100%$0.05
Lowest unit price——
Cost of 1M in + 200k out$0.36 +502.8%$0.06
Context262K8K +96.9%
Max output262K—
Providers305 +83.3%
RegionsCH, EU, GLOBAL, 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-msvideotext
Returnstexttext
TypeText modelsText models
Free optionnono
Cheapest provideraihubmixhuggingface

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

huggingface, jiekou, novita, requesty, trustedrouter

Frequently asked questions

Which is cheaper, Qwen3.5 397B-A17B or Sao10K Stheno 8b?

Sao10K Stheno 8b is 70% cheaper than Qwen3.5 397B-A17B on input price. Sao10K Stheno 8b is 95% cheaper than Qwen3.5 397B-A17B on output price. Sao10K Stheno 8b is 83% cheaper than Qwen3.5 397B-A17B on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3.5 397B-A17B or Sao10K Stheno 8b?

Qwen3.5 397B-A17B: 262K tokens; Sao10K Stheno 8b: 8K tokens.

Where can I use both Qwen3.5 397B-A17B and Sao10K Stheno 8b?

huggingface, jiekou, novita, requesty, trustedrouter