Qwen: Qwen3 Coder 480B A35B
Provider: qwen · qwen/qwen3-coder
How Qwen: Qwen3 Coder 480B A35B pricing compares
At $1 / 1M output tokens, Qwen: Qwen3 Coder 480B A35B is the 23rd-cheapest of 51 qwen models we track. It's cheaper than 67% of the 392 paid models on computetrail (131st-cheapest overall). Output costs 3.3× its input price ($0.3 / 1M in). For a typical 3:1 input-to-output workload that works out to about $0.47 / 1M blended. Reading cached input costs 67% less than fresh input, so prompt caching cuts repeat-context cost sharply. Its 262,144 tokens context window ranks 219th-largest of 392 models with a published limit.
Output price history
Across 60 daily snapshots since 2026-06-29, the output price has fallen 44.4% — from $1.8 to $1 / 1M.
Similar-priced models
| Model | Provider | Output $/1M | Context |
|---|---|---|---|
| DeepSeek: DeepSeek V3.1 Terminus | deepseek | $1 | 163,840 |
| Perplexity: Sonar | perplexity | $1 | 127,072 |
| MiniMax: MiniMax M2 | minimax | $1.02 | 204,800 |
| DeepSeek: DeepSeek V3 | deepseek | $1.0287 | 163,840 |
| Google: Gemini 3.7 Flash (batch) | $0.9375 | 1,048,576 | |
| MiniMax: MiniMax M2.5 | minimax | $1.08 | 204,800 |
Prices are recorded daily from public provider data via OpenRouter and normalized to USD per 1M tokens. See methodology.