AI Rate CardQwen3 235B-A22B vs Sao10k L3 8B Lunaris: API price and specs
Sao10k L3 8B Lunaris is 83% cheaper than Qwen3 235B-A22B on input price.
Sao10k L3 8B Lunaris is 91% cheaper than Qwen3 235B-A22B on output price.
Sao10k L3 8B Lunaris is 86% cheaper than Qwen3 235B-A22B on a 1M-in / 200k-out workload.
Qwen3 235B-A22B has a 3100% larger context than Sao10k L3 8B Lunaris.
| Field | Qwen3 235B-A22B | Sao10k L3 8B Lunaris |
|---|---|---|
| Lowest input, per 1M | $0.18 +500% | $0.03 |
| Median input, per 1M | $0.21 +322% | $0.05 |
| Lowest output, per 1M | $0.54 +980% | $0.05 |
| Median output, per 1M | $0.80 +1500% | $0.05 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.29 +620% | $0.04 |
| Context | 262K | 8K +96.9% |
| Max output | 82K | — |
| Providers | 13 | 3 +76.9% |
| Regions | US | — |
| Accepts | image, text, video | text |
| Returns | text | — |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | deepinfra | deepinfra |
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
Frequently asked questions
Which is cheaper, Qwen3 235B-A22B or Sao10k L3 8B Lunaris?
Sao10k L3 8B Lunaris is 83% cheaper than Qwen3 235B-A22B on input price. Sao10k L3 8B Lunaris is 91% cheaper than Qwen3 235B-A22B on output price. Sao10k L3 8B Lunaris is 86% cheaper than Qwen3 235B-A22B on a 1M-in / 200k-out workload.
Which has the larger context, Qwen3 235B-A22B or Sao10k L3 8B Lunaris?
Qwen3 235B-A22B: 262K tokens; Sao10k L3 8B Lunaris: 8K tokens.
Where can I use both Qwen3 235B-A22B and Sao10k L3 8B Lunaris?
deepinfra, jiekou, requesty