Qwen: Qwen-Plus
Provider: qwen · qwen/qwen-plus
How Qwen: Qwen-Plus pricing compares
At $0.78 / 1M output tokens, Qwen: Qwen-Plus is the 19th-cheapest of 51 qwen models we track. It's cheaper than 72% of the 392 paid models on computetrail (112th-cheapest overall). Output costs 3.0× its input price ($0.26 / 1M in). For a typical 3:1 input-to-output workload that works out to about $0.39 / 1M blended. Reading cached input costs 80% less than fresh input, so prompt caching cuts repeat-context cost sharply. Its 1,000,000 tokens context window ranks 127th-largest of 392 models with a published limit.
Output price history
Across 60 daily snapshots since 2026-06-29, the output price has held steady at $0.78 / 1M — no change so far.
Similar-priced models
| Model | Provider | Output $/1M | Context |
|---|---|---|---|
| Meta: Llama 4 Maverick | meta-llama | $0.8 | 1,048,576 |
| DeepSeek: R1 Distill Llama 70B | deepseek | $0.8 | 8,192 |
| Z.ai: GLM 4.5 Air | z-ai | $0.85 | 131,072 |
| Meta: Llama 3.3 70B Instruct | meta-llama | $0.71 | 131,072 |
| DeepSeek: DeepSeek V4 Flash Vision Exp | deepseek | $0.66 | 1,048,576 |
| Z.ai: GLM 4.6V | z-ai | $0.9 | 131,072 |
Prices are recorded daily from public provider data via OpenRouter and normalized to USD per 1M tokens. See methodology.