PRICEDeepSeek V4 Flash via OpenRouter: output price ↓ 33%2mPRICEDeepSeek V4 Flash via OpenRouter: input price ↓ 33%2mPRICE~moonshotai/kimi-latest input_per_mtok decreased from 1.39 to 1.343mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0086 to 0.00383mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0086 to 0.00383mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.012 to 0.00513mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.012 to 0.00513mPRICEdeepseek/deepseek-v4-flash cached_input_per_mtok decreased from 0.0084 to 0.00563mPRICEdeepseek/deepseek-v4-flash output_per_mtok decreased from 0.084 to 0.0563mPRICEdeepseek/deepseek-v4-flash input_per_mtok decreased from 0.042 to 0.0283mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.013 to 0.008634mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.013 to 0.008634mCAPABILITYxiaomi/mimo-v2.6-flash now declares support for top_logprobs34mCAPABILITYxiaomi/mimo-v2.6-flash now declares support for logprobs34mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.017 to 0.01234mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.017 to 0.01234mPRICE~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 Scaleway

#3 of 4 providers for GLM-5.2 · #5 of 6 models on Scaleway · EU
Compare with other providers
Score89.7Rel.100.0%Tools100.0%JSON100.0%TTFT282 msP951630 msTok/s91Price$2.06 / $6.30Ctx1M217 results · last 152m ago

GLM-5.2 on other providers

ProviderScoreTTFTTok/s$ Out
Together96.0271 ms283$4.40
Cortecs94.2425 ms142$3.33
ScalewayTHIS PAGE89.7282 ms91$6.30
OpenRouter82.2480 ms137$3.99

Other models on Scaleway

ModelScoreTTFT$ Out
GPT-OSS 120B91.6179 ms$0.69
Llama 3.3 70B89.9144 ms$1.03
DeepSeek V4 Flash87.6389 ms$0.92
Qwen3-235B85.9162 ms$2.58
GLM-5.2THIS PAGE80.8282 ms$6.30
Mistral Medium 3.580.7164 ms$8.60