---
id: "cerebras"
site: "cerebras.ai"
headquarters: "US"
gateways: ["hf", "openrouter", "vercel"]
models: 8
endpoints: 11
tokens_week: 3001930992
token_share: "0.0%"
rank: 68
cheapest_on: "0 of 11 shared models"
cheaper_than: "0% of offers at the median"
vs_card: "275% over the card price at the median over 1 models"
cache_hit: "65.4%"
uptime_1d: 100.0000
latency_p50_ms: 269
tokens_per_second: 831
trains_on_some: false
retains_on_some: true
quantization: "fp16 (4)"
---
# Cerebras

`alibaba/qwen3.8-27b`, `google/gemma-4-31b-it`, `google/gemma-4-31B-it`, `openai/gpt-oss-120b`, `qwen/qwen3.8-27b`, `Qwen/Qwen3.8-27B`, `z-ai/glm-4.7`, `zai/glm-4.7`