> Kimi
The official Moonshot AI developer platform for Kimi models. Offers pay-as-you-go access to Kimi K3, K2.7-Code, and K2.6 over an OpenAI-compatible API. One-off trial credits available upon verification.
// pros
- A genuinely callable API: OpenAI-compatible, so swapping base_url + api_key works with the openai SDK
- Run directly by a first-tier Chinese model vendor (Moonshot AI) rather than a relay, so there is no upstream-key-theft concern
- One-off credits after real-name verification allow a zero-cost integration check
- Long context is a genuine strength: K3 supports a 1M-token window, K2.6 and K2.7-Code support 256K
- Already integrated by mainstream tools such as Vercel and Cursor, with mature docs and console
// cons
- No permanently free model at all; once the credits are gone it is fully pay-as-you-go, so it is fundamentally a paid platform
- Claiming the credits requires personal real-name verification (phone number plus identity data), a real privacy cost
- The flagship K3 is excluded from the trial credits, so testing K3 requires topping up first
- Credits expire and the amount is small; CNY 15 (≈$2.23) buys very few tokens at K3 prices
- Models iterate fast and old versions are retired (the kimi-k2 series was retired on 2026-05-25), so integrations must track versions
- The exact free/trial rules live in scattered promotional announcements rather than a single official page; the figures found come mostly from community tutorials
Treat this as a vendor's paid API platform, not a source of free LLM capacity. The CNY 15 (≈$2.23) credit covers an integration check and small-scale evaluation at best; after that you pay, and the flagship K3 needs a top-up first. If your workload genuinely needs long context (1M on K3, 256K on K2.6/K2.7) it is a reasonable paid option; if the goal is sustained zero-cost calling, this site does not meet it and a platform with a real ongoing free tier is a better fit. Signup requires real-name verification, so weigh the privacy cost. Keep model names configurable so a retired version does not break production.
community_reputation
The Kimi platform is Moonshot AI's official channel, with a clear corporate entity and integrations from mainstream products such as Vercel and Cursor. Community discussion centres on model capability (long context, K2/K3 coding performance) and price, and is positive-to-neutral; no exit-scam, fraud or upstream-key-theft allegations were found. The contested point is the 'free' label: several tutorials and pricing reviews note that the developer API needs a top-up to activate, that there is no ongoing free tier, and that the CNY 15 (≈$2.23) newcomer voucher excludes the flagship K3 — which conflicts with how some 'free API roundup' articles present it.
imported analysis — independent third party, not Uprouter editorial · verify before relying on it
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: Not an ongoing free tier. New users who register and complete personal real-name verification receive roughly CNY 15 (≈$2.23) in one-off trial credits (time-limited), usable on the K2 family. The flagship K3 requires a prior top-up to unlock (community reports put the floor around CNY 10 (≈$1.49)), and the CNY 15 (≈$2.23) new-user voucher explicitly does not apply to K3. On the USD-priced side there is a promotional 'top up USD 5, get a USD 5 voucher' offer. Once credits are spent the platform is purely paid; no permanently free model is offered.
| Plan | Type | Monthly | Input /1M | Output /1M | Note |
|---|---|---|---|---|---|
| Free tier (source-reported) | free | — | — | — | Not an ongoing free tier. New users who register and complete personal real-name verification receive roughly CNY 15 (≈$2.23) in one-off trial credits (time-limited), usable on the K2 family. The flagship K3 requires a prior top-up to unlock (community reports put the floor around CNY 10 (≈$1.49)), and the CNY 15 (≈$2.23) new-user voucher explicitly does not apply to K3. On the USD-priced side there is a promotional 'top up USD 5, get a USD 5 voucher' offer. Once credits are spent the platform is purely paid; no permanently free model is offered. |
| Kimi K2.6 | payg | — | $0.950 | $4.00 | — |
Pricing normalized from public sources — always verify with the provider.
<a href="https://uprouter.online/s/platform-kimi-com" target="_blank" rel="noopener"><img src="https://uprouter.online/badge/platform-kimi-com.svg" alt="Kimi 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 Kimi entry — no tracking, no scripts.
$ Does Kimi have a free tier?
Yes — Kimi offers a free tier that we value at roughly $2.23 in free credits (estimate — derived from rate-limited usage at pay-as-you-go prices). Always confirm current limits on Kimi's official pricing page — free tiers change without notice.
$ How much does Kimi cost per 1M tokens?
Kimi 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 Kimi safe to use?
Uprouter rates Kimi 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 Kimi through Uprouter Connect?
Yes — Kimi is Connect-compatible. Add your Kimi 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.
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 →best-effort probes · not a guarantee · last 13h ago
| Checked | Status | Latency |
|---|---|---|
| 13h ago | up | 745ms |
| 14h ago | up | 730ms |
| 1d ago | down | 6001ms |
| 2d ago | up | 714ms |
| 3d ago | up | 759ms |
| 4d ago | up | 727ms |
| 12d ago | up | 208ms |
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
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": "sandbox-echo",
"messages": [{ "role": "user", "content": "Hello via Kimi" }]
}'Metered in Uprouter compute — the usage log shows which upstream served each request and its exact cost.
Ranked by neutral similarity signals only — live status, Connect compatibility, free-tier shape and free-credit proximity. Commercial relationships never influence this list.