yangmao.ai · Python setup money page
SiliconFlow Python API Setup
Use this page when you need a working Python starting point for SiliconFlow, then validate quota and model names in the official console before production.
Quick verdict
- Free API: ¥14
- Rate limits: Varies by model/account (RPM, TPM, context, and queue limits)
- Best model starting point: DeepSeek-V3 (hosted)
- Mainland China access: direct or relatively friendly
Provider fit matrix
SiliconFlow buyer intent notes
Who should care
Best for China-access model routing, free/low-cost hosted open models, and teams comparing DeepSeek, Qwen, GLM, and image models in one console.
Decision trigger
Shortlist SiliconFlow when domestic reachability and multi-model routing are both required.
Watch out: Validate free-model queue priority, RPM/TPM, context limits, and paid fallback pricing per model.
Production readiness checklist
Python setup snapshot
Start with the smallest possible chat completion, then move the key to your server-side secret manager before production.
from openai import OpenAI
client = OpenAI(
api_key="your-siliconflow-key",
base_url="https://api.siliconflow.cn/v1"
)
response = client.chat.completions.create(
model="Qwen/Qwen2.5-7B-Instruct", # 免费模型
messages=[{"role": "user", "content": "你好"}],
)
print(response.choices[0].message.content)Free API and pricing notes
¥14
¥14 free credits on signup, some smaller hosted models are free/zero-price; always confirm the current free model list, RPM/TPM, context, and queue limits before production.
Access and production risk
Mainland China friendly / direct path likely
Chinese service, direct access in mainland China. Top choice for Chinese developers to access open-source model APIs.
How to set it up
Create or locate your provider API key in the official dashboard.
Install the OpenAI-compatible Python SDK or the provider-supported SDK.
Set the API key in an environment variable instead of hard-coding secrets.
Run a small SiliconFlow chat completion with DeepSeek-V3 (hosted).
Watch free credits, RPM/TPM limits, response shape, and error messages before scaling.
Credit-change alerts
Want to know when free credits, pricing, or availability changes? Subscribe first, then compare official providers, API gateways, and alternatives.
Subscribe → Get an OpenLLMAPI key → Compare API gateways →Related internal links
Source snapshot
Data source: yangmao.ai provider YAML tracker plus provider docs reviewed by the daily crawler. Official dashboards can change quota and pricing without notice; verify before production.
- yangmao.ai provider id
- siliconflow
- Official source
- https://siliconflow.cn
- Last updated
- 2026-05-26
- Free tier
- Free model access varies by model; RPM/TPM and context limits should be checked in the console
- API credits
- ¥14
- Rate limit
- Varies by model/account (RPM, TPM, context, and queue limits)
- Access note
- Chinese service, direct access in mainland China. Top choice for Chinese developers to access open-source model APIs.
FAQ
Does SiliconFlow have a free API?
Yes. Current yangmao.ai record: ¥14. Rate limit note: Varies by model/account (RPM, TPM, context, and queue limits).
Is SiliconFlow OpenAI-compatible?
The recorded setup uses an OpenAI-compatible pattern or SDK-style call. Validate the latest base URL and model names in SiliconFlow docs.
Can I use SiliconFlow from mainland China?
SiliconFlow is marked as relatively direct or Mainland-China-friendly in the current tracker.
What should I do when SiliconFlow credits run out?
Compare the alternatives below, check /en/free-ai-api/, and shortlist official providers or API gateway options before production.
Is SiliconFlow mainly an API gateway?
It functions as a China-friendly model platform/router, so it is useful when you need several hosted models without maintaining separate provider integrations.