Cerebras

Cerebras is an AI model provider.Tokenando tracks 4 Cerebras models, with input pricing from $0.1000/M and an average blended cost of $0.6205/M. Its flagship model is Llama-3.3-70B (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 ↗

ModelsUSD per million tokens. Blend is 70% input, 30% output, our calculation.

MODELS TRACKED
4
3 categories
FLAGSHIP
Llama-3.3-70B (Cerebras)
Via API
MIN INPUT
$0.1000/M
cheapest model in family
AVG BLENDED
$0.6205/M
across 4 priced models
MAX CONTEXT
128,000
largest window in family

Frequently Asked Questions

How many models does Cerebras offer?

Tokenando tracks 4 Cerebras models.

How much do Cerebras models cost?

Cerebras model input pricing starts at $0.1000 per million tokens, with an average blended cost of $0.6205 per million across the 4 priced models we track.

What is Cerebras's flagship model?

Cerebras's flagship model is Llama-3.3-70B (Cerebras). It is the highest-tier Cerebras model we track, with input pricing of $0.5900 per million tokens.

What model categories does Cerebras cover?

Cerebras covers 3 categories: frontier, reasoning and efficient.

Terms used on this page