Claude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/MPaLM 2 Bison$0.500/MPaLM 2 Unicorn$5.000/MGemma 3 27B$0.270/MGrok 3$6.600/MGrok 2$4.400/MGrok 1.5$8.000/MDeepSeek-V3$0.519/MDeepSeek-V3-0324$0.519/MDeepSeek-R1$1.042/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/MPaLM 2 Bison$0.500/MPaLM 2 Unicorn$5.000/MGemma 3 27B$0.270/MGrok 3$6.600/MGrok 2$4.400/MGrok 1.5$8.000/MDeepSeek-V3$0.519/MDeepSeek-V3-0324$0.519/MDeepSeek-R1$1.042/M
BETA
Subscribe
← All providers·AI model pricing index
Cerebras

Cerebras

Wafer-scale silicon — currently the fastest hosted Llama 3 inference on the market. Throughput-optimised, not feature-rich.

Founded 2016HQ Sunnyvale, USAWebsite ↗Official pricing ↗API docs ↗
MODELS TRACKED
4
3 categories
FLAGSHIP
Llama-3.3-70B (Cerebras)
efficient
MIN INPUT
$0.100/M
cheapest model in family
AVG BLENDED
$0.621/M
across 4 priced models
MAX CONTEXT
128K
largest window in family
Frontier
1 model
Llama-3.1-405B (Cerebras)profile
frontier · 128K ctx
in $0.990/Mout $0.990/M
405B wafer-scale
Reasoning
1 model
DeepSeek-R1 (Cerebras)profile
reasoning · 64K ctx
in $0.550/Mout $0.990/M
R1 on Cerebras
Efficient
2 models
Llama-3.3-70B (Cerebras)profile
efficient · 128K ctx
in $0.590/Mout $0.990/M
Fastest 70B inference
Llama-3.1-8B (Cerebras)profile
efficient · 128K ctx
in $0.100/Mout $0.100/M
Fastest 8B ever