ERNIE 4.5 300B A47B vs Qwen 2.5 72B Instruct
Qwen 2.5 72B Instruct is cheaper on output tokens, while ERNIE 4.5 300B A47B offers a larger context window. Choose ERNIE 4.5 300B A47B or Qwen 2.5 72B Instruct based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | ERNIE 4.5 300B A47B | Qwen 2.5 72B Instruct |
|---|---|---|
| Provider | NovitaAI | NovitaAI |
| Input / 1M tokens | $0.28 | $0.38 |
| Output / 1M tokens | $1.10 | $0.40 |
| Context window | 123K | 32K |
| Parameters | — | — |
| Open weights | Yes | Yes |
| Released | Jun 2025 | Oct 2024 |
FAQ
Is ERNIE 4.5 300B A47B or Qwen 2.5 72B Instruct cheaper?
Qwen 2.5 72B Instruct is cheaper on output tokens ($0.40 vs $1.10 per 1M).
Which has the larger context window, ERNIE 4.5 300B A47B or Qwen 2.5 72B Instruct?
ERNIE 4.5 300B A47B has the larger context window (123K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.