
Cerebras: Models Quality, Performance & Price
Analysis of Cerebras's models across key metrics including quality, price, output speed, latency, context window & more. This analysis is intended to support you in choosing the best model provided by Cerebras for your use-case. For more details including relating to our methodology, see our FAQs. Models analyzed: Llama 3.3 70B, Llama 3.1 8B, and DeepSeek R1 Distill Llama 70B.
Link:
Cerebras Model Comparison Summary
Quality:
Llama 3.1 8B and
Llama 3.3 70B are the highest quality models offered by Cerebras, followed by
DeepSeek R1 Distill Llama 70B.Output Speed (tokens/s):
Llama 3.1 8B (2204 t/s) and
Llama 3.3 70B (2201 t/s) are the fastest models offered by Cerebras, followed by
DeepSeek R1 Distill Llama 70B.Latency (seconds):
Llama 3.3 70B (0.23s) and
Llama 3.1 8B (0.25s) are the lowest latency models offered by Cerebras, followed by
DeepSeek R1 Distill Llama 70B.Blended Price ($/M tokens):
Llama 3.1 8B ($0.10) and
Llama 3.3 70B ($0.94) are the cheapest models offered by Cerebras, followed by
DeepSeek R1 Distill Llama 70B.Context Window Size:
DeepSeek R1 Distill Llama 70B (66k) and
Llama 3.3 70B (33k) are the largest context window models offered by Cerebras, followed by
Llama 3.1 8B.





Highlights
Quality
Artificial Analysis Quality Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
Parallel Queries:
Prompt Length:
Key definitions
Artificial Analysis Quality Index: Average result across our evaluations covering different dimensions of model intelligence. Currently includes MMLU, GPQA, Math & HumanEval. OpenAI o1 model figures are preliminary and are based on figures stated by OpenAI. See methodology for more details.
Context window: Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).
Output Speed: Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).
Latency: Time to first token of tokens received, in seconds, after API request sent. For models which do not support streaming, this represents time to receive the completion.
Price: Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Output Price: Price per token generated by the model (received from the API), represented as USD per million Tokens.
Input Price: Price per token included in the request/message sent to the API, represented as USD per million Tokens.
Time period: Metrics are 'live' and are based on the past 14 days of measurements, measurements are taken 8 times a day for single requests and 2 times per day for parallel requests.