PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.04 to 0.6027mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.01327mPRICE~deepseek/deepseek-flash-latest cached_input_per_mtok decreased from 0.0021 to 0.002127mPRICEdeepseek/deepseek-v4.1-flash cached_input_per_mtok increased from 0.0021 to 0.00627mPRICEdeepseek/deepseek-v4.1-flash output_per_mtok increased from 0.68 to 1.2027mPRICEdeepseek/deepseek-v4.1-flash input_per_mtok increased from 0.015 to 0.3027mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0077 to 0.001157mPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.28 to 1.0457mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0077 to 0.003857mPRICE~deepseek/deepseek-flash-latest cached_input_per_mtok decreased from 0.02 to 0.002157mPRICE~deepseek/deepseek-flash-latest output_per_mtok increased from 0.60 to 0.6857mPRICE~deepseek/deepseek-flash-latest input_per_mtok decreased from 0.02 to 0.01557mPRICEdeepseek/deepseek-v4.1-flash cached_input_per_mtok decreased from 0.02 to 0.002157mPRICEdeepseek/deepseek-v4.1-flash output_per_mtok increased from 0.60 to 0.6857mPRICEdeepseek/deepseek-v4.1-flash input_per_mtok decreased from 0.02 to 0.01557mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0077 to 0.01757mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0077 to 0.01757mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.012 to 0.00771hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.012 to 0.00771hPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.012 to 0.00771hPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.012 to 0.00771hPRICEdeepseek/deepseek-v3.1-terminus input_per_mtok decreased from 0.30 to 0.271hPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok increased from 0.0011 to 0.0122hPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok increased from 0.60 to 1.282hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.013 to 0.0122hPRICEdeepseek/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 0.0122hNEW MODELnvidia/switchyard appeared in the catalogue2hPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.04 to 0.603hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.0133hPRICEnvidia/nemotron-3-ultra-550b-a55b cached_input_per_mtok decreased from 0.12 to 0.103hPRICEnvidia/nemotron-3-ultra-550b-a55b output_per_mtok decreased from 2.40 to 2.203hPRICEnvidia/nemotron-3-ultra-550b-a55b input_per_mtok decreased from 0.60 to 0.503hPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0051 to 0.0173hPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0051 to 0.0173hPRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.293hPRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.363hPRICE~moonshotai/kimi-latest input_per_mtok decreased from 1.39 to 1.003hPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok increased from 0.95 to 1.043hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0058 to 0.00383h

Same model. Different infrastructure. Different result.

Global provider ranking

92 providers · 1030 models · 26 endpoints
#1 OverallCerebras99.0FastestCerebras0.41 sBest valueGroqEurope #1Mistral93.2Best toolsCerebras100.0%Best structuredCerebras100.0%
#ProviderΔ30d
01CerebrasBEST OVERALL● MEASUREDUS · Serverless · 1 model · 1 region100.0%100.0%100.0%1843230.4s1749P88↑ 0.0
02GroqBEST VALUE● MEASUREDUS · Serverless · 2 models · 1 region100.0%100.0%100.0%2613850.9s708P100↑ 0.1
03MistralBEST EUROPEANEU RESIDENT● MEASUREDFR · Serverless · 2 models · 1 region100.0%100.0%91.7%30710094.4s109P25↓ 0.1
04ScalewayEU RESIDENTEU OWNED● MEASUREDFR · Serverless · 6 models · 1 region100.0%100.0%100.0%17212344.7s93P38↑ 4.3
05CortecsEU RESIDENTEU OWNED● MEASUREDAT · Routed · 11 models · 1 region99.9%99.6%98.3%42512635.0s125P75↑ 4.3
06OpenAISOLE SERVER● MEASUREDUS · Serverless · 2 models · 1 region100.0%100.0%100.0%104024535.4s96P13↓ 0.8
07Together● MEASUREDUS · Serverless · 6 models · 1 region98.6%99.7%96.8%57216254.0s130P50↑ 5.5
08OpenRouter● MEASUREDUS · Routed · 13 models · 2 regions99.5%99.9%96.4%65630275.9s91P63↑ 8.1
8 of 18 providers ranked · · Methodology →
01Cerebras99.0
Best overallUS · Serverless · 1 model · 1 region
TTFT184 ms
Rel.100.0%
Tok/s1749
$ Out$0.75
Tools100.0%
Δ30d0.0
View dossier
02Groq98.2
Best valueUS · Serverless · 2 models · 1 region
TTFT261 ms
Rel.100.0%
Tok/s708
$ Out$0.45
Tools100.0%
Δ30d+0.1
View dossier
03Mistral93.2
Best EuropeanFR · Serverless · 2 models · 1 region
TTFT307 ms
Rel.100.0%
Tok/s109
$ Out$4.50
Tools100.0%
Δ30d-0.1
View dossier
04Scaleway92.4
FR · Serverless · 6 models · 1 region
TTFT172 ms
Rel.100.0%
Tok/s93
$ Out$1.81
Tools100.0%
Δ30d+4.3
View dossier
05Cortecs92.1
AT · Routed · 11 models · 1 region
TTFT425 ms
Rel.99.9%
Tok/s125
$ Out$1.23
Tools99.6%
Δ30d+4.3
View dossier
06OpenAI90.4
US · Serverless · 2 models · 1 region
TTFT1040 ms
Rel.100.0%
Tok/s96
$ Out$15.60
Tools100.0%
Δ30d-0.8
View dossier
07Together86.6
US · Serverless · 6 models · 1 region
TTFT572 ms
Rel.98.6%
Tok/s130
$ Out$1.12
Tools99.7%
Δ30d+5.5
View dossier
08OpenRouter84.3
US · Routed · 13 models · 2 regions
TTFT656 ms
Rel.99.5%
Tok/s91
$ Out$1.20
Tools99.9%
Δ30d+8.1
View dossier
8 of 18 providers ranked · · Methodology →
Benchmark Partners · Become a Founding Partner →

Provider discovery

All 92 providers →
Recently benchmarked
European providersEuropean infrastructure →
Registry

92 providers · 1030 observed models · 26 catalogued endpoints, live from continuous discovery.

How we benchmark →