Qwen/Qwen2.5-72B-Instruct
siliconflow / Qwen/Qwen2.5-72B-Instruct
Input price
$0.59
per 1M tokens
Output price
$0.59
per 1M tokens
Context
33K
tokens
Capabilities
— Reasoning✓ Tool calls— Image input✓ Open weights
| Context | 33,000 tokens |
| max output | 4,000 tokens |
| Released | 2024-09-18 |
| Data updated | 2025-11-25 |
⚠ The two sources disagree on price
models.dev says $0.59, LiteLLM says $0.36. We do not average or guess — both raw values are in models.json, see for yourself.
Prices are official/data-source rates (per 1M tokens), not what relays actually charge — relay prices vary with discounts and group multipliers. See methodology.
Other models from this provider
ByteDance-Seed/Seed-OSS-36B-Instruct$0.21 · 262Kdeepseek-ai/DeepSeek-R1$0.5 · 164Kdeepseek-ai/DeepSeek-V3$0.25 · 164Kdeepseek-ai/DeepSeek-V3.1$0.27 · 164Kdeepseek-ai/DeepSeek-V3.1-Terminus$0.27 · 164Kdeepseek-ai/DeepSeek-V3.2$0.27 · 164Kdeepseek-ai/DeepSeek-V3.2-Exp$0.27 · 164KDeepSeek V4 Flash$0.13 · 1,000K