UPROUTERONLINE

> SiliconFlow

edit
api.siliconflow.cn

SiliconFlow (SiliconCloud) is a premier Chinese AI model platform offering high-performance inference for a wide range of open-source models (Qwen, Llama, DeepSeek). It is notable for providing free, permanent API access to models with parameters under 9B, alongside competitive pay-as-you-go rates for larger flagship

up· 1005msbest-effort probe · checked 13h agoupvotes · community
Official free tierFreemiumLow risk· conf 90%verifiedconnect: Pooled
Free credits
$2.38est.
Signup grants ~CNY 14 (≈$2.08) credit, plus ~CNY 16 (≈$2.38) voucher after real-name verification; many <=9B open-source models (Qwen2.5-7B, Llama3.1-8B, etc.) are permanently free; direct access within mainland China. Since 2026-05-15, unverified users are capped at 10 RPM and delinquent/unverified accounts are cut off.
Cheapest input /1M
USD per 1M input tokens, best tracked model
Cheapest output /1M
USD per 1M output tokens, best tracked model
Models tracked
2
Canonical models with normalized pricing
// source_analysisthird-party review via freeairouter.com

// pros

  • Legitimate company (Alibaba Cloud led its Series A; SiliconCloud has 3M+ users), credible and fairly stable
  • <=9B open-source models are permanently free, OpenAI-compatible, direct within mainland China, low barrier
  • Signup credit plus real-name voucher lets you use DeepSeek and other large models free for a while

// cons

  • Permanent-free is limited to <=9B small models; DeepSeek etc. rely on credit and cost money once exhausted
  • Free/low tiers hit 60s timeouts at peak, with noticeable rate fluctuation (recovers after IP change)
  • Since 2026-05-15 unverified users are capped at 10 RPM, directly affecting GitHub-login-only light users

Good for domestic users to try small models free and briefly use DeepSeek-class large models on credit; for production or stability, verify identity and pay per usage, and mind peak-time throttling.

community_reputation

Positive reputation: Securities Times and iFeng confirm its 100M-yuan funding, Alibaba-Cloud-led round and 3M+ users; CSDN/SegmentFault tutorials widely recommend its free allowance and OpenAI-compatible ease. Negatives are mainly peak-time throttling/timeouts and tightened real-name requirements. A legitimate big-vendor first-party free tier, no run-away risk.

imported analysis — independent third party, not Uprouter editorial · verify before relying on it

// free_quota
$2.38estimated value

How we estimated this: the free allowance is converted to a dollar value using the provider’s own pay-as-you-go rates for the models a typical developer would reach for. When the allowance is metered in requests, tokens or minutes rather than dollars, we assume median usage of the cheapest capable model. Because assumptions are involved, the figure carries the est. flag — treat it as an order of magnitude, not a quote.

note: Signup grants ~CNY 14 (≈$2.08) credit, plus ~CNY 16 (≈$2.38) voucher after real-name verification; many <=9B open-source models (Qwen2.5-7B, Llama3.1-8B, etc.) are permanently free; direct access within mainland China. Since 2026-05-15, unverified users are capped at 10 RPM and delinquent/unverified accounts are cut off.

// pricinglast verified 4d ago
PlanTypeMonthlyInput /1MOutput /1MNote
Free tier (source-reported)freeSignup grants ~CNY 14 (≈$2.08) credit, plus ~CNY 16 (≈$2.38) voucher after real-name verification; many <=9B open-source models (Qwen2.5-7B, Llama3.1-8B, etc.) are permanently free; direct access within mainland China. Since 2026-05-15, unverified users are capped at 10 RPM and delinquent/unverified accounts are cut off.
Free Tier (Small Models)freeUnlimited free access to models <9B parameters (e.g., Llama 3.1 8B, Qwen2.5 7B).
PAYG (Large Models)payg$1.11$3.89GLM-5.3 rate (converted from ¥8/¥28 at 7.2 rate).
Signup Bonusfree¥14 (approx. $2) credit for new users.
pricing_last_verified: 4d agoofficial pricing page

Pricing normalized from public sources — always verify with the provider.

// model prices

ModelInput /1MOutput /1MContext
Qwen2.5-7B-Instruct
Llama-3.1-8B-Instruct131k
// embed_badgebadge · uprouter.online/badge/api-siliconflow-cn
<a href="https://uprouter.online/s/api-siliconflow-cn" target="_blank" rel="noopener"><img src="https://uprouter.online/badge/api-siliconflow-cn.svg" alt="SiliconFlow live status on UPROUTER.ONLINE" height="40"></a>

Paste this into your README, docs or status page. The badge shows the same best-effort probe data as the directory, refreshes automatically, and links back to the full SiliconFlow entry — no tracking, no scripts.

SiliconFlow live status badge preview
// follows site theme
// faq
$ Does SiliconFlow have a free tier?

Yes — SiliconFlow offers a free tier that we value at roughly $2.38 in free credits (estimate — derived from rate-limited usage at pay-as-you-go prices). Always confirm current limits on SiliconFlow's official pricing page — free tiers change without notice.

$ How much does SiliconFlow cost per 1M tokens?

SiliconFlow does not publish simple per-1M-token pricing (it may bill per request, per output, or via a subscription plan). Check their official pricing page for exact figures.

$ Is SiliconFlow safe to use?

Uprouter rates SiliconFlow as low risk. Rated low risk. an official provider with a free tier with pricing, authentication and terms documented on its own site. The model coverage is consistent with a real upstream, so data and reliability risk are modest. Risk ratings are editorial, evidence-based, and never influenced by affiliate relationships.

$ Can I use SiliconFlow through Uprouter Connect?

Yes — SiliconFlow is Connect-compatible. Add your SiliconFlow API key in Uprouter Connect (encrypted at rest) and route requests to it through one OpenAI- and Claude-compatible API, optionally behind failover aliases. Uprouter meters the traffic in compute at the provider's listed rate.

// community0 reviews

Raw community sentiment, shown unblended. Votes never feed into objective data fields like price, risk, or status — and never into sort order.

No published reviews yet — be the first.

// more_informationprice history · live status · risk & confidence · code snippets

price_history

No recorded changes yet.

live_status

full history →
up · 70msup · 1144msup · 874msup · 1104msup · 1239msup · 1198msup · 1005ms
100%
7-probe uptime
7/30-day charts →

best-effort probes · not a guarantee · last 13h ago

CheckedStatusLatency
13h agoup1005ms
1d agoup1198ms
1d agoup1239ms
2d agoup1104ms
3d agoup874ms
4d agoup1144ms
12d agoup70ms

Uprouter runs its own probes; best-effort, not a guarantee. Probe results depend on our network location and cadence — for production, always use the provider’s own status page.

risk_&_confidence

Low risk
90%

Rated low risk. an official provider with a free tier with pricing, authentication and terms documented on its own site. The model coverage is consistent with a real upstream, so data and reliability risk are modest.

Confidence reflects how much verifiable evidence (official docs, probe history, community reports) backs this entry. Risk is our editorial assessment of operator reliability and terms — not financial advice.

code_snippets

curl https://uprouter.online/api/connect/v1/chat/completions \  -H "Authorization: Bearer upr_live_YOUR_KEY" \  -H "Content-Type: application/json" \  -d '{
    "model": "qwen2-5-7b-instruct",
    "messages": [{ "role": "user", "content": "Hello via SiliconFlow" }]
  }'

Metered in Uprouter compute — the usage log shows which upstream served each request and its exact cost.

// similar_providersscored by Official free tier signals

Ranked by neutral similarity signals only — live status, Connect compatibility, free-tier shape and free-credit proximity. Commercial relationships never influence this list.

Uprouter command palette

Jump to a page, provider, model or action

Keyboard shortcuts

Every keyboard shortcut available on Uprouter