Provider · 7 models · synced 2026-08-11

Cerebras API pricing

Every Cerebras model with a published rate, sorted cheapest first. Prices are USD per million tokens.

Cheapest input
$0.10
llama3.1-8b
Dearest input
$2.25
zai-glm-4.7
Token counting
estimated
no public tokenizer
Model Input Cached Output Context Long-ctx in
llama3.1-8b $0.10 — $0.10 128K —
gpt-oss-120b $0.35 — $0.75 131K —
qwen-3-32b $0.40 — $0.80 128K —
llama3.1-70b $0.60 — $0.60 128K —
llama-3.3-70b $0.85 — $1.20 128K —
zai-glm-4.6 dep $2.25 — $2.75 128K —
zai-glm-4.7 $2.25 — $2.75 128K —

Other providers