Skip to content

Cerebras

Pricing page

30 listings across 11 models

Data policies

from the provider's published policies

Headquarters: USPrivacy policyTerms of serviceStatus page

On training

For clarity, the foregoing does not grant Cerebras the right to use Service Content for the purpose of training or fine-tuning models.

Source: cerebras.ai/terms-of-service

On where data is processed

your data may be stored and processed in the United States and other countries outside the United States, which may have data protection laws that differ from the laws in your country.

Possible sources (2)

We take these statements from Cerebras's own published policies each time we refresh the data, so they can change or disappear when those pages do. Check with the provider before you rely on any of this.

Sold by Cerebras

7 listings sold by Cerebras.

Default order. Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
Qwen 3.8 27Bfp16
$0.99cache read $0.99$1.4966KNot measured
Gemma 4 31B ITcerebras/gemma-4-31b · fp16
$0.99$1.49131K
GPT OSS 120Bfp16
$0.35$0.75131K
Qwen3 32B
$0.40$0.80128KNot measured
Llama 3.3 70B Instructllama-3.3-70b
$0.85$1.20128KNot measured
Not enough data yet$0.60$0.60128KNot enough data yetNot measured
Llama 3.1 8B
Not enough data yet$0.10$0.10128KNot enough data yetNot measured

Run by Cerebras

15 listings where Cerebras runs the model. Another provider sells these listings.

Default order. Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
Qwen 3.8 27B
 Hugging Face$0.99$1.4966KNot measured
Gemma 4 31B ITgemma-4-31b
 Llmgateway$0.99$1.49Not published by the provider
GLM 4.7zai-glm-4.7
 Llmgateway$2.25$2.75Not published by the provider
GLM 4.6zai-glm-4.6
 Llmgateway$2.25$2.75Not published by the providerNot measured
GPT OSS 120B
 Eden AI$0.35$0.75131K
Qwen3 32B
 Llmgateway$0.40$0.80Not published by the providerNot measured
Llama 3.3 70B Instructllama-3.3-70b
 Llmgateway$0.85$1.20Not published by the providerNot measured
Llama 3.1 8B Instruct
 Hugging Face$0.10$0.10Not published by the providerNot measuredNot measured
Show all 15 listings

Showing 8 of 15: one listing for each model.

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)

How this data works