PRICEDeepSeek V4 Flash via OpenRouter: output price ↓ 33%12mPRICEDeepSeek V4 Flash via OpenRouter: input price ↓ 33%12mPRICE~moonshotai/kimi-latest input_per_mtok decreased from 1.39 to 1.3412mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0086 to 0.003812mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0086 to 0.003812mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.012 to 0.005112mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.012 to 0.005112mPRICEdeepseek/deepseek-v4-flash cached_input_per_mtok decreased from 0.0084 to 0.005612mPRICEdeepseek/deepseek-v4-flash output_per_mtok decreased from 0.084 to 0.05612mPRICEdeepseek/deepseek-v4-flash input_per_mtok decreased from 0.042 to 0.02812mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.013 to 0.008643mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.013 to 0.008643mCAPABILITYxiaomi/mimo-v2.6-flash now declares support for top_logprobs43mCAPABILITYxiaomi/mimo-v2.6-flash now declares support for logprobs43mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.017 to 0.01243mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.017 to 0.01243mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok increased from 0.0058 to 0.0131hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0058 to 0.0131hCAPABILITYopenai/gpt-5.4-image-2 no longer declares support for stop1hCAPABILITYopenai/gpt-5.4-image-2 no longer declares support for presence_penalty1hCAPABILITYopenai/gpt-5.4-image-2 no longer declares support for logit_bias1hCAPABILITYopenai/gpt-5.4-image-2 no longer declares support for frequency_penalty1hCAPABILITYopenai/gpt-5-image-mini no longer declares support for stop1hCAPABILITYopenai/gpt-5-image-mini no longer declares support for presence_penalty1hCAPABILITYopenai/gpt-5-image-mini no longer declares support for logit_bias1hCAPABILITYopenai/gpt-5-image-mini no longer declares support for frequency_penalty1hCAPABILITYopenai/gpt-5-image no longer declares support for stop1hCAPABILITYopenai/gpt-5-image no longer declares support for presence_penalty1hCAPABILITYopenai/gpt-5-image no longer declares support for logit_bias1hCAPABILITYopenai/gpt-5-image no longer declares support for frequency_penalty1hPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0077 to 0.0171hPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0077 to 0.0171hPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0086 to 0.00582hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0086 to 0.00582hPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.012 to 0.00772hPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.012 to 0.00772hPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.013 to 0.00862hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.013 to 0.00862hPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.017 to 0.0122hPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.017 to 0.0122h

GLM-5.2 on Fireworks

Not yet measured

Fireworks serves GLM-5.2 (declared in its catalogue), but this pair has not yet been measured from the canonical vantage. Benchmarks appear here with the first canonical run. See measured providers for GLM-5.2 →