PRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0086 to 0.005124mPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.60 to 1.2824mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0086 to 0.005124mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.012 to 0.005124mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.012 to 0.005124mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.013 to 0.008655mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.013 to 0.008655mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.017 to 0.01255mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.017 to 0.01255mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok increased from 0.0038 to 0.0131hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.0131hPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0051 to 0.0171hPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0051 to 0.0171hNEW MODELinclusionai/ling-3.1-flash appeared in the catalogue1hPRICEDeepSeek V4 Flash via OpenRouter: output price ↓ 33%2hPRICEDeepSeek V4 Flash via OpenRouter: input price ↓ 33%2hPRICE~moonshotai/kimi-latest input_per_mtok decreased from 1.39 to 1.342hPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0086 to 0.00382hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0086 to 0.00382hPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.012 to 0.00512hPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.012 to 0.00512hPRICEdeepseek/deepseek-v4-flash cached_input_per_mtok decreased from 0.0084 to 0.00562hPRICEdeepseek/deepseek-v4-flash output_per_mtok decreased from 0.084 to 0.0562hPRICEdeepseek/deepseek-v4-flash input_per_mtok decreased from 0.042 to 0.0282hPRICE~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 0.00862hCAPABILITYxiaomi/mimo-v2.6-flash now declares support for top_logprobs2hCAPABILITYxiaomi/mimo-v2.6-flash now declares support for logprobs2hPRICEdeepseek/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 0.0122hPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok increased from 0.0058 to 0.0133hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0058 to 0.0133hCAPABILITYopenai/gpt-5.4-image-2 no longer declares support for stop3hCAPABILITYopenai/gpt-5.4-image-2 no longer declares support for presence_penalty3hCAPABILITYopenai/gpt-5.4-image-2 no longer declares support for logit_bias3hCAPABILITYopenai/gpt-5.4-image-2 no longer declares support for frequency_penalty3hCAPABILITYopenai/gpt-5-image-mini no longer declares support for stop3hCAPABILITYopenai/gpt-5-image-mini no longer declares support for presence_penalty3hCAPABILITYopenai/gpt-5-image-mini no longer declares support for logit_bias3hCAPABILITYopenai/gpt-5-image-mini no longer declares support for frequency_penalty3h

Groq vs Together

2 shared models · US vs US · independent benchmarks

Registry facts

FactGroqTogether
Typeinference hostinference host
HeadquartersUSUS
Catalogued endpoints11
EU residencyNoNo

GPT-OSS 120B: Groq vs Together

● MEASURED Groq detail → · ● MEASURED Together detail →

MetricGroqTogether
TTFT p50264 ms182 ms
TTFT p95402 ms467 ms
Throughput486 tok/s138 tok/s
Reliability100%93.5%
Tool calling100%100%
Structured output100%85.7%
$ output / M tokens$0.60$0.60

Every figure above is an independent measurement from the canonical vantage; unmeasured fields show — until measured. How we benchmark →