BENCHMARKFirst benchmarks recorded: MiniMax M3 → Cortecs → ?5hBENCHMARKFirst benchmarks recorded: Kimi K3 → Cortecs → ?5hBENCHMARKFirst benchmarks recorded: DeepSeek V4 Pro → Cortecs → ?5hBENCHMARKFirst benchmarks recorded: GLM-4.7 → Cortecs → ?5hBENCHMARKFirst benchmarks recorded: GLM-5.2 → Cortecs → ?5h

Llama 3.3 70B on Nebius

#2 of 10 providers for Llama 3.3 70B · #3 of 3 models on Nebius · EU
Compare with other providers
Score91.8Rel.98.8%Tools98.0%JSON99.3%TTFT213 msP95778 msTok/s192Price$0.07 / $0.22Ctx128k3,944 runs · last 15m ago · DEV DATA

Llama 3.3 70B on other providers

ProviderScoreTTFTTok/s$ Out
Fireworks91.9231 ms251$0.48
NebiusTHIS PAGE91.8213 ms192$0.22
Groq89.2132 ms1013$0.32
Cerebras88.5110 ms2835$0.66
OpenRouter76.8284 ms216$0.48
Scaleway75.1263 ms130$0.40
Together74.4297 ms176$0.40
Nextbit72.1252 ms113$0.24
DeepInfra69.7379 ms119$0.20
OVHcloud64.0275 ms100$0.37

Other models on Nebius

ModelScoreTTFT$ Out
Qwen3-235B97.0288 ms$0.40
DeepSeek-V396.8340 ms$0.50
Llama 3.3 70BTHIS PAGE95.9213 ms$0.22