AI Rate Card

Qwen 2.5 72B Instruct vs Qwen3.5 Plus 2026-02-15: API price and specs

Qwen 2.5 72B Instruct is 12% cheaper than Qwen: Qwen3.5 Plus 2026-02-15 on input price.

Qwen 2.5 72B Instruct is 74% cheaper than Qwen: Qwen3.5 Plus 2026-02-15 on output price.

Qwen 2.5 72B Instruct is 46% cheaper than Qwen: Qwen3.5 Plus 2026-02-15 on a 1M-in / 200k-out workload.

Qwen: Qwen3.5 Plus 2026-02-15 has a 700% larger context than Qwen 2.5 72B Instruct.

FieldQwen 2.5 72B InstructQwen: Qwen3.5 Plus 2026-02-15
Lowest input, per 1M$0.23$0.26 +13%
Median input, per 1M$0.36 +38.5%$0.26
Lowest output, per 1M$0.40$1.56 +290%
Median output, per 1M$0.40$1.56 +290%
Lowest unit price——
Cost of 1M in + 200k out$0.31$0.57 +84.5%
Context131K +87.5%1M
Max output16K +75%66K
Providers114 +63.6%
RegionsUSGLOBAL
Acceptstextimage, text, video
Returnstexttext
TypeText modelsText models
Free optionnono
Cheapest providerrequestyedenai

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

edenai, kilo, openrouter, trustedrouter

Frequently asked questions

Which is cheaper, Qwen 2.5 72B Instruct or Qwen: Qwen3.5 Plus 2026-02-15?

Qwen 2.5 72B Instruct is 12% cheaper than Qwen: Qwen3.5 Plus 2026-02-15 on input price. Qwen 2.5 72B Instruct is 74% cheaper than Qwen: Qwen3.5 Plus 2026-02-15 on output price. Qwen 2.5 72B Instruct is 46% cheaper than Qwen: Qwen3.5 Plus 2026-02-15 on a 1M-in / 200k-out workload.

Which has the larger context, Qwen 2.5 72B Instruct or Qwen: Qwen3.5 Plus 2026-02-15?

Qwen 2.5 72B Instruct: 131K tokens; Qwen: Qwen3.5 Plus 2026-02-15: 1M tokens.

Where can I use both Qwen 2.5 72B Instruct and Qwen: Qwen3.5 Plus 2026-02-15?

edenai, kilo, openrouter, trustedrouter