Qwen
Qwen raises API prices for three models on OpenRouter
Por ahora esta nota solo está disponible en inglés.
Qwen increased API prices for three models on OpenRouter effective November 4, 2026, compared with November 3, 2026.
Precio en OpenRouter, por 1M de tokens
- 0,14 US$
- 0,80 US$
- 0,15 US$
- 0,60 US$
- 0,09 US$
- 1,10 US$
Qwen3 235B A22B Instruct 2507
Input price rose 55.6% to $0.14 per million tokens from $0.09, and output price rose 45.5% to $0.80 per million tokens from $0.55. The model has 235.1B total parameters with 22B activated parameters, 94 layers, 128 experts with 8 activated, and supports 262,144 tokens natively extendable to 1,010,000 tokens, according to Qwen. Qwen says on the MMLU-Pro benchmark the model scores 83.0, on GPQA it scores 77.5, and on AIME25 it scores 70.3.
Qwen3 Coder 30B A3B Instruct
Input and output prices each rose 114.3% to $0.15 and $0.60 per million tokens from $0.07 and $0.28 respectively. The model has 30.5B parameters and a 262,144-token context window.
Qwen3 Next 80B A3B Instruct
Input price rose 11.1% to $0.10 per million tokens from $0.09, while output price remained at $1.10 per million tokens. The model has 81.3B parameters and a 262,144-token context window.
Puntos clave
- Qwen3 235B A22B Instruct 2507 saw the largest absolute price increases across both input and output.
- Qwen3 Coder 30B A3B Instruct experienced the highest percentage increase at 114.3% for both input and output.
- Qwen3 Next 80B A3B Instruct had a modest input increase with no change to output pricing.