PRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0062 to 0.00478mPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok increased from 1.28 to 1.608mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0062 to 0.00478mPRICE~deepseek/deepseek-pro-latest cached_input_per_mtok decreased from 0.13 to 0.00428mPRICE~deepseek/deepseek-pro-latest output_per_mtok decreased from 3.50 to 0.408mPRICE~deepseek/deepseek-pro-latest input_per_mtok decreased from 0.13 to 0.138mPRICE~deepseek/deepseek-flash-latest cached_input_per_mtok increased from 0.017 to 0.0198mPRICE~deepseek/deepseek-flash-latest input_per_mtok increased from 0.017 to 0.0198mPRICEqwen/qwen3.5-35b-a3b output_per_mtok decreased from 1.30 to 1.008mPRICEqwen/qwen3.5-35b-a3b input_per_mtok decreased from 0.16 to 0.158mPRICEdeepseek/deepseek-v4.1-flash cached_input_per_mtok increased from 0.017 to 0.0198mPRICEdeepseek/deepseek-v4.1-flash input_per_mtok increased from 0.017 to 0.0198mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0062 to 0.0178mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0062 to 0.0178mPRICEKimi K3 via OpenRouter: output price ↑ 12%38mPRICE~z-ai/glm-latest cached_input_per_mtok decreased from 0.18 to 0.06739mPRICE~z-ai/glm-latest output_per_mtok decreased from 2.65 to 1.1439mPRICE~z-ai/glm-latest input_per_mtok increased from 0.11 to 0.1239mPRICE~z-ai/glm-flash-latest cached_input_per_mtok decreased from 0.033 to 0.02639mPRICE~z-ai/glm-flash-latest output_per_mtok increased from 0.53 to 0.6339mPRICE~z-ai/glm-flash-latest input_per_mtok decreased from 0.033 to 0.02639mPRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.35 to 0.2939mPRICE~moonshotai/kimi-latest output_per_mtok increased from 10.00 to 11.2039mPRICE~moonshotai/kimi-latest input_per_mtok increased from 0.35 to 1.1339mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0087 to 0.006239mPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.34 to 1.2839mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0087 to 0.006239mPRICE~deepseek/deepseek-flash-latest cached_input_per_mtok decreased from 0.022 to 0.01739mPRICE~deepseek/deepseek-flash-latest output_per_mtok increased from 0.63 to 0.7539mPRICE~deepseek/deepseek-flash-latest input_per_mtok decreased from 0.022 to 0.01739mPRICEmoonshotai/kimi-k3 cached_input_per_mtok decreased from 0.35 to 0.2939mPRICEmoonshotai/kimi-k3 output_per_mtok increased from 10.00 to 11.2039mPRICEmoonshotai/kimi-k3 input_per_mtok increased from 0.35 to 1.1339mPRICEdeepseek/deepseek-v4.1-flash cached_input_per_mtok decreased from 0.022 to 0.01739mPRICEdeepseek/deepseek-v4.1-flash output_per_mtok increased from 0.63 to 0.7539mPRICEdeepseek/deepseek-v4.1-flash input_per_mtok decreased from 0.022 to 0.01739mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.0092 to 0.006239mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.0092 to 0.006239mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.01 to 0.00871hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.01 to 0.00871h

Fireworks vs Scaleway

Not yet comparable

Fireworks and Scaleway share 3 declared models, but a head-to-head publishes only when both sides carry canonical measurements on a shared model. See the live ranking →