UPROUTERONLINE

> ModelScope

edit
modelscope.cn

ModelScope (modelscope.cn), backed by Alibaba Cloud, is an open-source model community and inference platform. It provides a free API tier allowing users to make up to 2,000 OpenAI-compatible calls per day across a wide range of open-source models (Qwen, DeepSeek, GLM).

up· 1972msbest-effort probe · checked 13h agoupvotes · community
Official free tierFreemiumLow risk· conf 88%verifiedconnect: BYOK
Free credits
$60.00est.
2,000 API-Inference calls/day per user (verified, aggregated across models; ~200-500/day per model), resets UTC+8 00:00, 429 when exceeded; requires Alibaba Cloud binding. ~$60/mo equivalent at ~1K tokens/call.
Cheapest input /1M
USD per 1M input tokens, best tracked model
Cheapest output /1M
USD per 1M output tokens, best tracked model
Models tracked
5
Canonical models with normalized pricing
// source_analysisthird-party review via freeairouter.com

// pros

  • First-party platform with Alibaba Cloud compute — high credibility and fairly stable, no run-away/key-theft risk
  • 2000 free calls/day, OpenAI-compatible, configurable directly in clients like Cherry Studio
  • Free tier covers frontier open-source models (Qwen/DeepSeek/Kimi/GLM), rated one of the most underrated free AI platforms

// cons

  • Requires binding an Alibaba Cloud account, adding a small barrier
  • Individual models have stricter caps (Qwen3-Coder 500, DeepSeek-R1/V3.1 ~200/day); some users report throttling at ~500 calls
  • Popular models are 'delisted after a while', so the available-model list is unstable

Good for individuals and developers to call Qwen/DeepSeek/GLM etc. free for prototyping and learning; mind the Alibaba-Cloud binding, per-model caps and possible delisting of popular models — for production, evaluate Alibaba Cloud's formal service.

community_reputation

Positive reputation: official docs, Cherry Studio docs and Kingy AI confirm 2000 free daily calls, OpenAI compatibility, a rich model catalog, and that the Qwen family is most stable; negatives mainly concern the Alibaba-Cloud binding, stricter per-model caps (some throttled at 500) and occasional delisting of popular models. An Alibaba first-party free tier.

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

// free_quota
$60.00estimated 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: 2,000 API-Inference calls/day per user (verified, aggregated across models; ~200-500/day per model), resets UTC+8 00:00, 429 when exceeded; requires Alibaba Cloud binding. ~$60/mo equivalent at ~1K tokens/call.

// pricinglast verified 4d ago
PlanTypeMonthlyInput /1MOutput /1MNote
Free tier (source-reported)free2000 API-Inference calls/day per user, resetting at UTC+8 00:00, non-cumulative, returning 429 when exceeded; individual models have their own caps (e.g. Qwen3-Coder 500, DeepSeek-R1/V3.1 limited to ~200/day); base_url https://api-inference.modelscope.cn/v1; requires binding an Alibaba Cloud account.
Free tierfreeFreeFreedaily request caps
Free Tierfree2,000 calls per day aggregate; max 200 per model.
pricing_last_verified: 4d agoofficial pricing page

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

// model prices

ModelInput /1MOutput /1MContext
Qwen family (most stable)
DeepSeek-V3.1
Kimi
GLM family (per the current console availability)
DeepSeek-R164k
// embed_badgebadge · uprouter.online/badge/modelscope-cn
<a href="https://uprouter.online/s/modelscope-cn" target="_blank" rel="noopener"><img src="https://uprouter.online/badge/modelscope-cn.svg" alt="ModelScope 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 ModelScope entry — no tracking, no scripts.

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

Yes — ModelScope offers a free tier that we value at roughly $60.00 in free credits (estimate — derived from rate-limited usage at pay-as-you-go prices). Always confirm current limits on ModelScope's official pricing page — free tiers change without notice.

$ How much does ModelScope cost per 1M tokens?

ModelScope 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 ModelScope safe to use?

Uprouter rates ModelScope 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 ModelScope through Uprouter Connect?

Yes — ModelScope is Connect-compatible. Add your ModelScope 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 · 178msup · 1603msup · 1633msup · 1841msup · 2252msup · 1785msup · 1972ms
100%
7-probe uptime
7/30-day charts →

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

CheckedStatusLatency
13h agoup1972ms
14h agoup1785ms
1d agoup2252ms
2d agoup1841ms
3d agoup1633ms
4d agoup1603ms
12d agoup178ms

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
88%

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": "qwen-family-most-stable",
    "messages": [{ "role": "user", "content": "Hello via ModelScope" }]
  }'

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