qwen/qwen-2.5-72b-instruct
Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfrafp8 | $0.360 | $0.400 | 33K | 100% |
| Novitabf16 | $0.380 | $0.400 | 32K | — |
Qwen2.5 72B Instruct costs $0.360 per million input tokens and $0.400 per million output tokens via OpenRouter, making it 142nd cheapest of 298 paid models.
Qwen2.5 72B Instruct generates around 28 tokens per second with 436ms time-to-first-token (p50), the 246th fastest tracked model.
Qwen2.5 72B Instruct supports a 131K-token context window and can output up to 16K tokens. It accepts text input.