Skip to main content

Cerebras

Inference host

Cerebras runs open and licensed models on its own hardware and sells them by usage, often faster or cheaper than the maker.

PricingDocsStatusinfo@cerebras.ai
Visit cerebras.ai
Models2
Cheapest for
0 models
Serves
1 model types
Visits in September 2026802K−19.5%Unique visitors 346K
  1. Apr
  2. May
  3. Jun
  4. Jul
  5. Aug
  6. Sep
Models by type

Models on Cerebras

ModelInputOutputvs officialContext
Qwen3.8 27B$0.99/1M$1.49/1M
from $0.50 at EmpirioLabs AI
-50%—
GPT OSS 120B$0.35/1M$0.75/1M
from $0.14 at Requesty
+436%—

Cerebras at a glance

2 models in total: 2 text. The cheapest is GPT OSS 120B at $0.75 /1M. Qwen3.8 27B has the largest context window, 262K tokens. The most searched is Qwen3.8 27B, with about 120K Google searches a month. The newest is Qwen3.8 27B, released Aug 5, 2026.

Cheapest

  1. GPT OSS 120B$0.75/1M
  2. Qwen3.8 27B$1.49/1M

Largest context

  1. Qwen3.8 27B262K
  2. GPT OSS 120B131K

Most searched

  1. Qwen3.8 27B120K
  2. GPT OSS 120B35K

Newest

  1. Qwen3.8 27BAug 5, 2026
  2. GPT OSS 120BAug 4, 2025