Back to providers

SiliconFlow

HealthyTelemetry updated 36m ago

High-performance AI inference platform offering ultra-low latency and cost-effective access to open-source models. Supports models with up to 1M token context windows and OpenAI-compatible API endpoints.

API Base URL

https://api.siliconflow.cn/v1

Authentication

bearer

Uptime (24h)

100.0%

Uptime (7d)

100.0%

Supported Regions

ap-east-1us-west-2global

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

36m ago

Supported Models (5)

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

ModelPricing (per 1M)Rate LimitsRegions

DeepSeek R1

deepseek-r1

In: $0.55
Out: $2.19		300 RPM / 500K TPM
ap-east-1global

DeepSeek V4

deepseek-v4

In: $0.14
Out: $0.28		600 RPM / 1.0M TPM
ap-east-1global

Hy3 Preview

hy3-preview

In: $0.14
Out: $0.28		300 RPM / 500K TPM
ap-east-1global

Llama 3.3 70B Instruct

llama-3-3-70b

In: $0.35
Out: $0.35		600 RPM / 1.0M TPM
ap-east-1global

Qwen3 32B

qwen3-32b

In: $0.16
Out: $0.16		600 RPM / 1.0M TPM
ap-east-1global