Fresh paint, wet floors — we're rebuilding CostOfToken into a cross-provider price comparison. Some corners are still under construction; the full version is coming up soon.

Qwen2.5 VL 72B Instruct pricing

Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images. Qwen2.5 VL 72B Instruct from Alibaba (Qwen) costs $0.800 per 1M input tokens and $1.00 per 1M output tokens. Cached input is $0.400 per 1M. Context window 128,000 tokens.

API id qwen2.5-vl-72b-instruct · Alibaba (Qwen) · source · updated 2026-09-25 · general-purpose

$0.800
Input / 1M tokens
$1.00
Output / 1M tokens
$0.400
Cached input / 1M
128K
Context window

Qwen2.5 VL 72B Instruct specifications

API id
qwen2.5-vl-72b-instruct
Model type
general-purpose
Context window
128K tokens
Max output
115K tokens
Currency
USD
Price source
Provider API
Last checked
2026-09-25

Tags

  • vision

Qwen2.5 VL 72B Instruct across providers

The same model, priced by every seller we track. Ranked by the cost of 1M input + 1M output tokens, standard tier; savings measured against buying from the vendor directly.

ProviderInput /1MCached /1MOutput /1M1M in + 1M outvs vendor
Alibaba (Qwen)VendorCheapestviewing
$0.800$0.400$1.00$1.80—
$0.800$0.400$1.00$1.80—

What Qwen2.5 VL 72B Instruct costs in practice

Estimated cost at common usage volumes
WorkloadInput tokensOutput tokensEstimated cost
Short chat turn1,000500$0.0013
Document summary50,0002,000$0.04
1M tokens in, 200K out1,000,000200,000$1.00

Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.

Qwen2.5 VL 72B Instruct price history

RecordedInput /1MOutput /1M
2026-09-04$0.800$1.00
2026-08-26$0.250$0.750
2026-08-17$0.800$1.00
2026-08-11$0.250$0.750

Common questions

How much does Qwen2.5 VL 72B Instruct cost per 1M tokens?
Qwen2.5 VL 72B Instruct costs $0.800 per 1M input tokens and $1.00 per 1M output tokens on the standard tier. Cached input is $0.400 per 1M.
What is Qwen2.5 VL 72B Instruct's context window?
Qwen2.5 VL 72B Instruct accepts up to 128,000 tokens in a single request, and can return up to 115,200 output tokens.
Is there a cheaper Qwen model than Qwen2.5 VL 72B Instruct?
Yes. Qwen2.5 72B Instruct is $0.360 per 1M input tokens versus $0.800 for Qwen2.5 VL 72B Instruct, with a 32,768 token context window.
Where does this Qwen2.5 VL 72B Instruct price come from?
From the OpenRouter catalogue, because Alibaba (Qwen) does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from Alibaba (Qwen)'s own — verify before committing spend.

Head-to-head comparisons

Other Qwen models

See all Qwen pricing →