Chutes.ai
online
Decentralized inference on Bittensor. Pay-per-token, some free.
LLMest. 2024 · Decentralized (Bittensor)
87
/ 100 APIVault Score
// At a glance
Free Tier
Some free models · $0–$0.30/MTok · no card
Category
LLM
Credit Card
Not required
Last Verified
just now
// Free tier details
Available Models
Llama 3.3 70BDeepSeek-R1Qwen3Mistral
Monthly Requests
Select models free; others $0–$0.30/MTok
No credit card needed
No phone verification
// Quick start
300">"text-purple-400">from openai 300">"text-purple-400">import OpenAI
client = OpenAI(
api_key=300">"YOUR_CHUTES_KEY",
base_url=300">"https://llm.chutes.ai/v1",
)
response = client.chat.completions.create(
model=300">"unsloth/Llama-3.3-70B-Instruct",
messages=[{300">"role": 300">"user", 300">"content": 300">"Hello."}],
)
print(response.choices[0].message.content)// Overview
Chutes runs open-source models on donated and idle GPU capacity via the Bittensor network. Pricing is $0–$0.30/MTok depending on model — among the cheapest available. Some models remain free; the early-access 200 req/day free program ended Feb 2026.
// Pros
- Cheapest inference on the market ($0–$0.30/MTok)
- Decentralized — not dependent on one cloud
- OpenAI-compatible endpoint
// Cons
- Free 200 req/day program ended Feb 2026
- Speed varies based on donated GPU availability
- No uptime SLA
// Score breakdown
Reliability (35%) (from just now health check)100/100
Free Tier Generosity (30%) (computed from quota, no-CC, no-phone fields)85/100
Documentation (20%) (human rating)78/100
Popularity (15%) (GitHub stars (log-normalised), or manual baseline)70/100
Methodology: apivault.dev/methodology
// Best for
Ultra-budget inferenceBittensor ecosystemDeepSeek / Llama at near-zero cost
// Recent changes
Feb 27, 2026Early Access 200 req/day free program discontinuedfree tier changed