AI Rate Card

Qwen3-Next 80B-A3B Instruct vs Devstral Small 2505: API price and specs

Devstral Small 2505 is 44% cheaper than Qwen3-Next 80B-A3B Instruct on input price.

Devstral Small 2505 is 78% cheaper than Qwen3-Next 80B-A3B Instruct on output price.

Devstral Small 2505 is 63% cheaper than Qwen3-Next 80B-A3B Instruct on a 1M-in / 200k-out workload.

Qwen3-Next 80B-A3B Instruct has a 104.8% larger context than Devstral Small 2505.

FieldQwen3-Next 80B-A3B InstructDevstral Small 2505
Lowest input, per 1M$0.09 +80%$0.05
Median input, per 1M$0.14 +133.3%$0.06
Lowest output, per 1M$0.55 +360%$0.12
Median output, per 1M$1.18 +437.5%$0.22
Lowest unit price——
Cost of 1M in + 200k out$0.20 +170.8%$0.074
Context262K128K +51.2%
Max output262K4K +98.4%
Providers163 +81.2%
RegionsEU, GLOBAL, US—
Acceptsimage, text, videotext
Returnstexttext
TypeText modelsText models
Free optionnono
Cheapest providerdeepinfraio-net

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, io-net, trustedrouter

Frequently asked questions

Which is cheaper, Qwen3-Next 80B-A3B Instruct or Devstral Small 2505?

Devstral Small 2505 is 44% cheaper than Qwen3-Next 80B-A3B Instruct on input price. Devstral Small 2505 is 78% cheaper than Qwen3-Next 80B-A3B Instruct on output price. Devstral Small 2505 is 63% cheaper than Qwen3-Next 80B-A3B Instruct on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3-Next 80B-A3B Instruct or Devstral Small 2505?

Qwen3-Next 80B-A3B Instruct: 262K tokens; Devstral Small 2505: 128K tokens.

Where can I use both Qwen3-Next 80B-A3B Instruct and Devstral Small 2505?

deepinfra, io-net, trustedrouter