Back to providers

Anyscale

HealthyTelemetry updated 38m ago

Serverless inference platform built on Ray, offering high-throughput access to popular open-weight models. OpenAI-compatible API with competitive pricing and enterprise-grade scalability.

API Base URL

https://api.endpoints.anyscale.com/v1

Authentication

bearer

Uptime (24h)

100.0%

Uptime (7d)

100.0%

Supported Regions

us-east-1us-west-2

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

DeepSeek V4

deepseek-v4

In: $0.20
Out: $0.40
300 RPM / 500K TPM
us-east-1us-west-2

Llama 3.3 70B Instruct

llama-3-3-70b

In: $0.50
Out: $0.50
600 RPM / 1.0M TPM
us-east-1us-west-2

Llama 4 Maverick

llama-4-maverick

In: $0.25
Out: $0.25
600 RPM / 1.0M TPM
us-east-1us-west-2