> Chutes
Chutes is a decentralized serverless AI inference marketplace on Bittensor (Subnet 64). It provides an OpenAI-compatible API for deploying and scaling open-source models using high-performance VLLM templates, with per-token pricing and optional monthly subscription plans.
// pros
- OpenAI-compatible API with many open-weight models (DeepSeek/Llama/Mistral, etc.)
- Decentralized compute, pay-per-use with no minimum, often cheaper than mainstream clouds
- Already an upstream provider for aggregators like OpenRouter; sizeable (claims trillions of tokens/month)
// cons
- The original free tier is gone; it now essentially requires payment, and 'free' is no longer a stable selling point
- Pricing/free thresholds fluctuate with Bittensor subnet economics and TAO subsidies — unpredictable
- Execution by decentralized miners; the community has questioned model authenticity/quantization/consistency
- Privacy: requests pass through third-party miner nodes — be cautious with sensitive data
No longer qualifies as a 'free LLM API' (free tier removed); more of a cheap decentralized paid inference marketplace. Those willing to accept price volatility and model-authenticity risk can try pay-per-use — do not send sensitive data.
community_reputation
Chutes is fairly well-known in AI/crypto circles and is listed by IQ.wiki, Bittensor research, and several review sites; but its decentralized model raises authenticity/stability questions, and after removing the free tier its reputation shifted from 'a free DeepSeek source' to 'a cheap paid inference marketplace'.
imported analysis — independent third party, not Uprouter editorial · verify before relying on it
Free tier present — value not quantified
This provider offers a free tier, but its terms don’t convert cleanly into a USD figure (e.g. request-count limits or capacity-dependent pools). We refuse to print a misleading zero here. See the note below and the official pricing page for the exact limits.
note: Official announcement 2026-02-27: $5-deposit 200-requests/day plan closed to new users, fully retires 2026-03-15; now pay-per-token (or GPU by the second). Bittensor-subsidized cheap models are not a free tier.
| Plan | Type | Monthly | Input /1M | Output /1M | Note |
|---|---|---|---|---|---|
| Free tier (source-reported) | free | — | — | — | The early 'one-time $5 deposit for 200 requests/day' free tier has been removed; it is now pay-per-token with no subscription or minimum. Some models are near-free thanks to Bittensor TAO subsidies, but that depends on subsidies/miners and is unstable. |
| Free tier | free | — | Free | Free | daily-limited chutes |
| Subscription | subscription | — | — | — | higher daily limits |
| Pay-as-you-go | payg | — | $0.025 | $0.098 | Rate for Mistral-Nemo-Instruct-2407-TEE; prices vary by model. |
| Plus | subscription | $10.00/mo | — | — | Includes daily request quota and 6% off PAYG rates beyond quota. |
Pricing normalized from public sources — always verify with the provider.
// model prices
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Meta-Llama 3.1 | — | — | — |
| Mistral | — | — | — |
| DeepSeek V3.2 | — | — | 164k |
<a href="https://uprouter.online/s/chutes-ai" target="_blank" rel="noopener"><img src="https://uprouter.online/badge/chutes-ai.svg" alt="Chutes 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 Chutes entry — no tracking, no scripts.
$ Does Chutes have a free tier?
Yes — Chutes offers a free tier. Always confirm current limits on Chutes's official pricing page — free tiers change without notice.
$ How much does Chutes cost per 1M tokens?
Chutes 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 Chutes safe to use?
Uprouter rates Chutes as medium risk. Rated medium risk. a commercial aggregator routing to many upstreams with only partial transparency: some model coverage or pricing is confirmed, while other figures rest on third-party reports or a login-gated console. Risk ratings are editorial, evidence-based, and never influenced by affiliate relationships.
$ Can I use Chutes through Uprouter Connect?
Yes — Chutes is Connect-compatible. Add your Chutes 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 14h ago
| Checked | Status | Latency |
|---|---|---|
| 14h ago | up | 184ms |
| 1d ago | up | 286ms |
| 2d ago | up | 630ms |
| 3d ago | up | 174ms |
| 4d ago | up | 235ms |
| 12d ago | up | 1118ms |
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 medium risk. a commercial aggregator routing to many upstreams with only partial transparency: some model coverage or pricing is confirmed, while other figures rest on third-party reports or a login-gated console.
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": "meta-llama-3-1",
"messages": [{ "role": "user", "content": "Hello via Chutes" }]
}'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.