AI Rate CardQwen3 30B-A3B Instruct 2507 vs Devstral 2: API price and specs
Qwen3 30B-A3B Instruct 2507 is 78% cheaper than Devstral 2 on input price.
Qwen3 30B-A3B Instruct 2507 is 85% cheaper than Devstral 2 on output price.
Qwen3 30B-A3B Instruct 2507 is 81% cheaper than Devstral 2 on a 1M-in / 200k-out workload.
| Field | Qwen3 30B-A3B Instruct 2507 | Devstral 2 |
|---|---|---|
| Lowest input, per 1M | $0.09 | $0.40 +344.4% |
| Median input, per 1M | $0.10 | $0.42 +320% |
| Lowest output, per 1M | $0.30 | $2.00 +567.6% |
| Median output, per 1M | $0.30 | $2.10 +600% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.15 | $0.80 +433.6% |
| Context | 262K | 262K |
| Max output | 262K | 256K +2.3% |
| Providers | 11 | 5 +54.5% |
| Regions | GLOBAL, US | EU, GLOBAL |
| Accepts | image, text | file, text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | ambient | edenai |
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
cortecs, edenai, kilo, openrouter, requesty
Frequently asked questions
Which is cheaper, Qwen3 30B-A3B Instruct 2507 or Devstral 2?
Qwen3 30B-A3B Instruct 2507 is 78% cheaper than Devstral 2 on input price. Qwen3 30B-A3B Instruct 2507 is 85% cheaper than Devstral 2 on output price. Qwen3 30B-A3B Instruct 2507 is 81% cheaper than Devstral 2 on a 1M-in / 200k-out workload.
Which has the larger context, Qwen3 30B-A3B Instruct 2507 or Devstral 2?
Qwen3 30B-A3B Instruct 2507: 262K tokens; Devstral 2: 262K tokens.
Where can I use both Qwen3 30B-A3B Instruct 2507 and Devstral 2?
cortecs, edenai, kilo, openrouter, requesty