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.

Open official provider → Get one OpenAI-compatible key → Compare API gateway options →

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

Best fit Image generation prototypes, creative automation, and media workflows

Watch out Image/video credits can burn faster than chat tokens; test with small batches first

Production fallback Keep at least one compatible backup provider before shipping

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.

SiliconFlow free tierCredits and free-model notes SiliconFlow vs QwenRouter vs direct provider SiliconFlow China accessRegional access notes

Production readiness checklist

Quota gate Start inside ¥14; log usage before adding retries or batch jobs.

No-card check Try the free path first, then confirm whether billing is required for API keys, higher RPM, or production endpoints.

Regional smoke test Still run one request from your deployment region and from mainland China if users are there.

Source freshness Snapshot date: 2026-06-16; official quota and pricing can change without notice.

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.

SiliconFlow production validation table

Use this table before sending real users, scheduled agents, or paid traffic to SiliconFlow. The goal is to validate source freshness, quota behavior, regional access, and fallback needs instead of trusting a stale free-credit claim.

Check Pass condition If it fails

Signup and billing state Key creation works and the account can spend the recorded ¥14. Compare SiliconFlow alternatives or route through a gateway before inviting users.

First request from target region A minimal request succeeds from your deployment region and mainland-China test point if relevant. Do not ship cron jobs or public demos until latency, DNS, TLS, and auth are repeatable.

Quota, retry, and error shape Rate-limit behavior matches the current Varies by model/account (RPM, TPM, context, and queue limits) note or official dashboard values. Cap retries, add request logging, and keep a second route for 429/5xx bursts.

Cost per accepted task Real prompts stay within your target token, query, image-credit, or compute budget. Use cheaper primary routes, caching, shorter prompts, or fallback only after validation failure.

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 →

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: 2026-06-16
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.