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

ERNIE-4.5-21B-A3B-Thinking vs Qwen 2.5 72B Instruct

ERNIE-4.5-21B-A3B-Thinking is cheaper on output tokens, while ERNIE-4.5-21B-A3B-Thinking offers a larger context window. Choose ERNIE-4.5-21B-A3B-Thinking or Qwen 2.5 72B Instruct based on the trade-off between cost, context, and the benchmarks that matter for your use case.

SpecERNIE-4.5-21B-A3B-ThinkingQwen 2.5 72B Instruct
ProviderNovitaAINovitaAI
Input / 1M tokens$0.07$0.38
Output / 1M tokens$0.28$0.40
Context window131K32K
Parameters——
Open weightsYesYes
ReleasedSep 2025Oct 2024
ERNIE-4.5-21B-A3B-Thinking details →Qwen 2.5 72B Instruct details →

FAQ

Is ERNIE-4.5-21B-A3B-Thinking or Qwen 2.5 72B Instruct cheaper?

ERNIE-4.5-21B-A3B-Thinking is cheaper on output tokens ($0.28 vs $0.40 per 1M).

Which has the larger context window, ERNIE-4.5-21B-A3B-Thinking or Qwen 2.5 72B Instruct?

ERNIE-4.5-21B-A3B-Thinking 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.