EVA-Qwen2.5-72B-v0.2
by NanoGPT · family qwen · listed Sep 2025
Qwen instruction model for multilingual chat, reasoning, and tool use
Current rates USD per 1M tokens
Input$0.799
Output$0.799
Cache read—
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2- Context window
- 16K tokens
- Max output
- 8K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2025-09-25
- Last updated
- 2025-09-25
← All NanoGPT listings