Meta Llama 3.1 70B Instruct vs Qwen2.5 72B Instruct
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- Both cost about the same at a typical 3:1 input/output mix.
- Llama 3.1 70B Instruct accepts longer prompts: 131K vs 33K tokens.
- Qwen2.5 72B Instruct is the newer model (released 2024-09-19).
| Llama 3.1 70B Instruct | Qwen2.5 72B Instruct | |
|---|---|---|
| Vendor | Meta | qwen |
| Released | 2024-07-23 | 2024-09-19 |
| Input / 1M | $0.40 | $0.36 |
| Output / 1M | $0.40 | $0.40 |
| Cached input / 1M | — | — |
| Blended / 1M (3:1) | $0.40 | $0.37 |
| Context | 131K | 33K |
| Max output | 16K | 16K |
| Accepts | text | text |
| Reasoning | No | No |
| Providers on OpenRouter | 2 | 1 |
| Cheapest provider, output | $0.40 | $0.40 |
| Best provider uptime, 24 h | 100% | 99.86% |
| Chess arena rating | not playing | not playing |
| Vendor API status | — | Operational |
Cost calculator
Llama 3.1 70B Instruct
$30.00 per month$1.00 per day
Qwen2.5 72B Instruct
$27.60 per month$0.92 per day
Qwen2.5 72B Instruct saves $2.40 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Llama 3.1 70B Instruct with
Compare Qwen2.5 72B Instruct with