Cerebras · synced 2026-08-11

llama-3.3-70b

Input / 1M
$0.85
Output / 1M
$1.20
Cached input
Context
128K

A 1,000-token prompt costs $0.00085 to send. Token counts for Cerebras models are estimated — approximated, because this family has no public tokenizer.

Priced closest to this

Model Provider Input Output
gemini-3.1-flash-live-preview Google $0.75 $4.50
gpt-5.4-mini OpenAI $0.75 $4.50
kimi-k2.6 Moonshot $0.95 $4.00
open-mixtral-8x7b Mistral $0.70 $0.70
codellama-70b-instruct Perplexity $0.70 $2.80
llama-2-70b-chat Perplexity $0.70 $2.80