Qwen2.5 72B Instruct pricing.

prices as of · 9 providers · 10 prices

Alibaba Cloud's Qwen2.5 72B Instruct holds 33k tokens of context. Open weights, so anyone may host it, which is why the prices below differ so much.

Qwen2.5 72B Instruct costs $0.36 in and $0.40 out per million tokens from OpenRouter, and no provider goes below it with a reason we can point at.

tool callingstructured outputopen weights33k contextreleased 19 Sept 2024

OpenRouter list price

$1.48/M tokens

$0.36 in · $0.40 out

read · 58% below the market median

Cheapest price we can explain

no price

Nobody goes below OpenRouter's price for a reason we can point at, so the list price is the one to beat. Every other price is below.

What it costs for your work

pages a month

OpenRouter list price

$0.24a month

cheapest we can explain

none

difference

no list price

A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.

Every provider selling Qwen2.5 72B Instruct

Four groups, decided by the price and by what the provider publishes about it. Prices are per million tokens, and the share is that row against OpenRouter's price. Alibaba Cloud trained Qwen2.5 72B Instruct and sells it on no catalog we read, so the price every row is measured against is OpenRouter's.

Same price as the maker

10 prices

The same price the maker charges, sold by someone else.

  • NanoGPT

    The same price OpenRouter charges.

    131k context hereNanoGPT

    $0.36 / $0.41in / out per M

    1.00×of list price

  • OpenRouter

    The same price OpenRouter charges.

    $0.36 / $0.40in / out per M

    1.00×of list price

  • Kilo Gateway

    The same price OpenRouter charges.

    $0.36 / $0.40in / out per M

    1.00×of list price

  • DeepInfra

    The same price OpenRouter charges.

    fp8 precisionDeepInfra

    $0.36 / $0.40in / out per M

    1.00×of list price

  • Nous Portal

    The same price OpenRouter charges.

    $0.36 / $0.40in / out per M

    1.00×of list price

  • Novita

    6% above OpenRouter's price.

    32k context hereNovita

    $0.38 / $0.40in / out per M

    1.04×of list price

  • Novita

    6% above OpenRouter's price.

    32k context herebf16 precisionNovita

    $0.38 / $0.40in / out per M

    1.04×of list price

  • Requesty

    6% above OpenRouter's price.

    32k context hereRequesty

    $0.38 / $0.40in / out per M

    1.04×of list price

  • Jiekou

    6% above OpenRouter's price.

    32k context hereJiekou

    $0.38 / $0.40in / out per M

    1.04×of list price

  • TrustedRouter

    11% above OpenRouter's price.

    32k context hereTrustedRouter

    $0.40 / $0.42in / out per M

    1.10×of list price

Frequently asked

Who sells Qwen2.5 72B Instruct cheapest?
No provider sells Qwen2.5 72B Instruct below OpenRouter's price with a reason we can point at. 9 providers sell it at or above list, and those prices are all on this page.
Is Qwen2.5 72B Instruct open weights?
Yes. Alibaba Cloud publishes the weights, so anyone may host Qwen2.5 72B Instruct, which is why 9 providers sell it and why their prices differ so much.
How much context does Qwen2.5 72B Instruct hold?
32,768 tokens in one call, which is about 33k, and it can call your own functions.
How does Qwen2.5 72B Instruct compare with the rest of the market?
At $1.48 per million tokens, OpenRouter's price is 58% below the $3.55 median across the 337 text models we track.
More from Alibaba CloudQwen3.8 27BQwen3.5 397B-A17BQwen3.6 35B-A3BQwen3 235B-A22BSimilar contextNano BananaMistral Small 3Qwen MaxVoxtral Small 24B 2507