Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

Qwen2.5 14B Instruct vs Aya Expanse 32B

Qwen2.5 14B Instruct is cheaper on output tokens, while Qwen2.5 14B Instruct offers a larger context window. Choose Qwen2.5 14B Instruct or Aya Expanse 32B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

SpecQwen2.5 14B InstructAya Expanse 32B
ProviderAlibabaCohere
Input / 1M tokens$0.35$0.50
Output / 1M tokens$1.40$1.50
Context window131K128K
Parameters——
Open weightsYesYes
ReleasedSep 2024Oct 2024
LMArena (Chatbot Arena) Elo score—1224
Qwen2.5 14B Instruct details →Aya Expanse 32B details →

FAQ

Is Qwen2.5 14B Instruct or Aya Expanse 32B cheaper?

Qwen2.5 14B Instruct is cheaper on output tokens ($1.40 vs $1.50 per 1M).

Which has the larger context window, Qwen2.5 14B Instruct or Aya Expanse 32B?

Qwen2.5 14B Instruct has the larger context window (131K tokens).

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.