Back to providers

Cerebras

HealthyTelemetry updated 38m ago

Ultra-fast inference provider powered by the Cerebras Wafer Scale Engine, known for extremely high tokens/sec throughput. Offers OpenAI-compatible API with free tier access.

API Base URL

https://api.cerebras.ai/v1

Authentication

api-key

Uptime (24h)

100.0%

Uptime (7d)

100.0%

Supported Regions

us-east-1

Latency (TTFT)

Time to first token percentiles

No latency data available

Health History

Uptime over the last 7 days

7-Day Uptime100.00% — Excellent
24-Hour Uptime100.00% — Excellent

Current Status

healthy

Last Checked

38m ago

Supported Models (3)

Models available through this provider. Click a model to view details.

ModelPricing (per 1M)Rate LimitsRegions

K2 Think

k2-think

In: $0.60
Out: $0.60
30 RPM / 60K TPM
us-east-1

Llama 3.3 70B Instruct

llama-3-3-70b

In: $0.60
Out: $0.60
30 RPM / 60K TPM
us-east-1

Llama 4 Scout

llama-4-scout

In: $0.60
Out: $0.60
30 RPM / 60K TPM
us-east-1