Models

Qwen2.5-72B-Instruct

hyperbolic · 131K ctx · 6 providers · updated 2026-08-05 00:15 UTC

Cheapest
$0.165 Official list · Hyperbolic
Avg price
$0.263 /1M · 1 outlier(s) excluded
providers
6
(3 × $0.120 + $0.300) ÷ 4 = $0.165/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.120, 3:1 $0.165, 1:1 $0.210, output only $0.300 per 1M.

The board shows this model's cheapest measured offer ($0.165/1M); the smaller figure under it is the mean of the 6 offers listed below ($0.263/1M). Add those up and divide — it matches. 1 offer(s) above 10x the median were left out of the average and flagged ⚠ in the table below — they are still listed, and still compete for the cheapest price.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
hyperbolic Pricebook (LiteLLM) $0.120$0.300 Official list
deepinfra Pricebook (LiteLLM) $0.120$0.390 Official list
nebius Pricebook (LiteLLM) $0.130$0.400 Official list
requesty Requesty $0.230$0.400 API-measured
deepinfra HuggingFace Router $0.360$0.400 1158ms 34 API-measured
novita HuggingFace Router $0.380$0.400 588ms 33 API-measured
burncloud ⚠ outlier burncloud $4.00$12.00 API-measured

Price trend

Cheapest blended price, last 31 days (USD/1M): $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165 → $0.165

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/qwen2.5-72b-instruct.json. Free reuse requires attribution to tkx.org.

About

Qwen2.5-72B-Instruct is a large language model served by multiple inference providers on AI model marketplaces, known for its capabilities in natural language understanding and generation.

AI-generated summary from public information — is this yours?

FAQ

How much does Qwen2.5-72B-Instruct cost?

Cheapest measured offer right now: $0.12/1M input, $0.3/1M output via hyperbolic — across 6 tracked providers, refreshed hourly.

Who serves Qwen2.5-72B-Instruct?

6 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

Is the price of Qwen2.5-72B-Instruct going up or down?

The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.

Related analysis

Back to rankings