Price comparison

Model	Input	Output	Cached input	Profile
`doubao-seed-2.0-lite` ByteDance Doubao	0.0519	0.31	0.0104	budgetfast
`glm-5.3-flash` Zhipu AI	0.0553	0.19	0.0159	budgetfast
`doubao-seed-2.1-lite` ByteDance Doubao	0.0691	0.23	0.0138	budgetfast
`mimo-v2.5` Xiaomi MiMo	0.0927	0.19	0.0019	budgetcheap cache
`deepseek-v4.1-flash` Not for U.S. federal use DeepSeek	0.14	0.55	0.0028	balancedcheap cache
`mimo-v2.5-pro` Xiaomi MiMo	0.28	0.56	0.0023	balancedcheap cache
`minimax-m3` MiniMax	0.36	1.43	0.0713	flagshiplong context
`doubao-seed-2.1-pro` ByteDance Doubao	0.52	2.59	0.10	flagship
`glm-5.3` Zhipu AI	0.55	1.94	0.14	flagship
`deepseek-v4-pro` Not for U.S. federal use DeepSeek	0.91	2.72	0.0302	flagship
`qwen3.8-max` Alibaba Qwen	1.51	4.53	0.19	flagshiplong context
`kimi-k3.1-pro` Moonshot AI	1.86	9.71	0.19	premiumlong context
`kimi-k3` Moonshot AI	2.20	11.00	0.22	premiumlong context

USD per 1 million tokens. Cached input applies when a prompt prefix is served from the provider's cache; it is billed separately and is far cheaper than fresh input.