> OpenRouter
OpenRouter is a commercial LLM gateway aggregating 500+ models from every major provider. It offers a single OpenAI-compatible API with a platform fee (5.5%) and a selection of free models for development.
// pros
- Legitimate company backed by a16z and Alphabet's CapitalG, processing 25T tokens/week — high operational credibility
- One OpenAI-compatible API aggregating 300+ models, including ~26 free ones, testable with no credit card
- Transparent privacy: no prompt/completion logging by default, control over routing to training providers, ZDR supported
- Transparent billing, no markup on upstream prices (only ~5.5% top-up fee)
// cons
- Free tier is clearly rate-limited (20 RPM, 50-1000/day), prone to timeouts under load, unsuitable for production
- Free models are mostly open-source/small-to-mid; flagship closed models still require payment
- Enabling opt-in prompt logging for a discount grants broader input/output usage rights — read the terms
As a legitimate commercial aggregator it is safe for experiments and non-sensitive prototypes; the free tier fits demos and learning, while production should upgrade to paid capacity and configure privacy/ZDR as needed.
community_reputation
Well-regarded and highly transparent: a16z and BusinessWire cover its funding and scale, official docs clearly document rate limits, privacy and billing, and third parties (DataStudios, CostGoat, Nudge Security) agree — the free tier suits demos/hackathons/prototypes, while production needs paid capacity and privacy review. It is a legitimate commercial aggregator, not a charity relay, with no run-away or key-theft risk.
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: :free models cost $0, no card; 20 req/min; 50 :free req/day with <10 credits, 1000/day after buying $10+ credits (verified FAQ; failed reqs count). ~$1.5/mo equivalent at 50 req/day, ~1K tokens/call.
| Plan | Type | Monthly | Input /1M | Output /1M | Note |
|---|---|---|---|---|---|
| Free tier (source-reported) | free | — | — | — | :free models are free and require no credit card; rate-limited to ~20 requests/minute, with 50 :free requests/day if you hold <10 credits, rising to 1000/day once you buy >=10 credits (failed requests also count). |
| Free tier | free | — | Free | Free | 50 req/day; 1,000 req/day with $10 lifetime top-up |
| Pay-as-you-go | payg | — | $1.25 | $10.00 | Example for Anthropic Claude 3.7. 5.5% platform fee applied to listed rates. |
Pricing normalized from public sources — always verify with the provider.
// model prices
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Auto Router | $-1000000.0000 | $-1000000.0000 | 2M |
| Free Models Router | Free | Free | 200k |
| nvidia/nemotron-nano-9b-v2:free | — | — | — |
| z-ai/glm-4.5-air (:free) | — | — | 131k |
| qwen/qwen3-next-80b-a3b-instruct:free | — | — | 262k |
| Gemma 4 31B | — | — | 262k |
| gpt-oss-120b | — | — | 131k |
| gpt-oss:20b | — | — | 131k |
| Llama 3.3 70B Instruct | — | — | 131k |
| Nemotron 3 Ultra | — | — | 256k |
| Qwen3 Coder | — | — | 262k |
<a href="https://uprouter.online/s/openrouter-ai" target="_blank" rel="noopener"><img src="https://uprouter.online/badge/openrouter-ai.svg" alt="OpenRouter 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 OpenRouter entry — no tracking, no scripts.
$ Does OpenRouter have a free tier?
Yes — OpenRouter offers a free tier that we value at roughly $1.50 in free credits (estimate — derived from rate-limited usage at pay-as-you-go prices). Always confirm current limits on OpenRouter's official pricing page — free tiers change without notice.
$ How much does OpenRouter cost per 1M tokens?
The cheapest model we track at OpenRouter is $-1000000.0000 per 1M input tokens and $-1000000.0000 per 1M output tokens. This is normalized from OpenRouter's published pricing — verify with the provider before purchasing, since prices change frequently.
$ Is OpenRouter safe to use?
Uprouter rates OpenRouter as low risk. Rated low risk. a commercial aggregator routing to many upstreams 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 OpenRouter through Uprouter Connect?
Yes — OpenRouter is Connect-compatible. Add your OpenRouter 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 | 49ms |
| 1d ago | up | 52ms |
| 1d ago | up | 60ms |
| 2d ago | up | 44ms |
| 3d ago | up | 69ms |
| 4d ago | up | 71ms |
| 12d ago | up | 604ms |
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. a commercial aggregator routing to many upstreams 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": "nvidia-nemotron-nano-9b-v2-free",
"messages": [{ "role": "user", "content": "Hello via OpenRouter" }]
}'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.