AI Rate CardQwen3 30B A3B vs deepseek-flash(1): API price and specs
Qwen3 30B A3B is 58% cheaper than deepseek-flash(1) on input price.
Qwen3 30B A3B is 41% cheaper than deepseek-flash(1) on output price.
Qwen3 30B A3B is 50% cheaper than deepseek-flash(1) on a 1M-in / 200k-out workload.
deepseek-flash(1) has a 681.2% larger context than Qwen3 30B A3B.
| Field | Qwen3 30B A3B | deepseek-flash(1) |
|---|---|---|
| Lowest input, per 1M | $0.0509 | $0.12 +135.8% |
| Median input, per 1M | $0.12 | $0.15 +25% |
| Lowest output, per 1M | $0.28 | $0.48 +68.4% |
| Median output, per 1M | $0.50 | $0.60 +20% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.11 | $0.22 +100.2% |
| Context | 128K +87.2% | 1M |
| Max output | 41K | — |
| Providers | 15 | 2 +86.7% |
| Regions | EU, GLOBAL, US | APAC |
| Accepts | image, text | image, text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | edenai | cometapi |
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 30B A3B or deepseek-flash(1)?
Qwen3 30B A3B is 58% cheaper than deepseek-flash(1) on input price. Qwen3 30B A3B is 41% cheaper than deepseek-flash(1) on output price. Qwen3 30B A3B is 50% cheaper than deepseek-flash(1) on a 1M-in / 200k-out workload.
Which has the larger context, Qwen3 30B A3B or deepseek-flash(1)?
Qwen3 30B A3B: 128K tokens; deepseek-flash(1): 1M tokens.
Where can I use both Qwen3 30B A3B and deepseek-flash(1)?
cometapi, edenai