Pricing

Per token. No subscription, no minimums, no "contact sales".

$0.25/M input · $2.09/M output · $0.04/M cached input
Qwen3.8-27B · 262,144-token context
WhatPrice per 1M tokensNotes
Input$0.25everything you send
Cached input$0.04repeated prompt prefixes, automatic — 6x cheaper
Output$2.09completions, including reasoning tokens

Billed monthly by invoice. Every request is journaled with its price snapshot — invoices are verifiable line by line. Volume pricing for sustained load: artem@llmtech.eu.

worked examples — not plans

There are no tiers and no subscriptions: everyone pays the same per-token rates above. These are just three workload profiles with the arithmetic done, so you know what a month adds up to.

If you run a chatbot

1M in + 100K out daily
30% cache hits

input $0.19 + output $0.21 per day

≈ $12/month

If you run an agent

3M in + 500K out daily
80% cache hits (repo context)

input $0.25 + output $1.05 per day

≈ $39/month

If you run bulk extraction

10M in + 300K out daily
50% cache hits

input $1.45 + output $0.63 per day

≈ $62/month

The cache rate is what makes agents and bulk workloads cheap here: repeated system prompts and document prefixes bill at $0.04 instead of $0.25.

against the market
ProviderInput, $/MOutput, $/M
LLM Tech$0.25$2.09
Chutes$0.35$2.75
DeepInfra$0.40$3.00
Alibaba Cloud$0.50$3.00

prices checked 2026-08-25 on public pricing pages; we intend to stay the lowest for this model.

Try the free trial key Get a production key