
SiliconCloud - Models as a Service
Overview
Prices on this page are standard billing units. Please refer to the following example for model billing. Specific pricing is based on the on-demand prices for different model APIs in the console.
· pro/deepseek-ai/deepseek-v3.1 Input: ¥4/M Tokens Output: ¥12/M Tokens · pro/deepseek-ai/deepseek-r1 Input: ¥4/M Tokens Output: ¥16/M Tokens · pro/deepseek-ai/deepseek-v3 Input: ¥2/M Tokens Output: ¥8/M Tokens · deepseek-ai/deepseek-r1-distill-qwen-32b: ¥1.26/M Tokens · Pro/BaAI/BGE-M3: ¥0.07/M Tokens · Qwen/Qwen3-235B-A22B Input: $2.5/M Tokens Output: $10/M Tokens · Qwen/Qwen3-30B-A3B Input: $0.7/M Tokens Output: $2.8/M Tokens · Qwen/Qwen3-32B Input: $1/M Tokens Output: $4/M Tokens · Qwen/Qwen3-14B Input: $0.5/M Tokens Output: $2/M Tokens · qwen/qwen2.5-vl-32b-instruct: ¥1.89/ M Tokens · qwen/qwen2.5-vl-72b-instruct: ¥4.13/ M Tokens · pro/qwen/qwen2.5-vl-7b-instruct: ¥0.35/ M Tokens · Qwen/Qwen3-Coder-480B-A35B-Instruct Input: ¥8/ M Tokens Output: ¥16/ M Tokens · pro/moonshotai/kimi-k2-instruct-0905 Input: ¥4/M Tokens Output: ¥16/ M Tokens
Highlights
- Fast reasoning - Self-developed efficient operators and optimization frameworks, leading inference acceleration engine in the world. - It maximizes throughput capacity and fully supports the business requirements of high-throughput scenarios. - Significantly optimized computational latency provides excellent performance guarantees for low latency scenarios.
- Cost-effective - Extreme end-to-end optimization, and significant reduction in inference and deployment costs. - Provide a flexible pay-as-you-go model to reduce resource waste and accurately control budgets.
- High stability - It has been verified by developers to ensure high reliability and stable operation. - Provide perfect monitoring and fault tolerance mechanisms to ensure service capabilities. - Provide professional technical support to meet the needs of enterprise-level scenarios and ensure high service availability.
Details
Pricing
SiliconCloud - Models as a Service
Usage costs (1)
Dimension | Cost/unit |
|---|---|
standard token usage price | CN¥0.001 |
Vendor refund policy
Cancellations and returns are currently not supported
Legal
Vendor terms and conditions
Content disclaimer
Usage information
Delivery details
Software as a Service (SaaS)
SaaS delivers cloud-based software products directly to customers over the internet. You can access these products through a subscription model. You will pay recurring monthly usage fees for your subscription.
Resources
Vendor resources
Support
Vendor support
Technical support contact information: aws-siliconcloud@siliconflow.cn
Amazon Web Services infrastructure support
Amazon Web Services Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.