Qwen2.5 VL 72B Instruct pricing.
Prices checked
Qwen2.5 VL 72B Instruct costs $0.80 in and $1 out per million tokens from OpenRouter; the cheapest price is $0.38 at Nebius Token Factory, checked .
OpenRouter's own price
OpenRouter
$0.80 in · $1 out
4% below the typical price of the 392 text models we track.
Cheapest price
Nebius Token Factory
$0.25 in · $0.75 out
56% less than OpenRouter, and the provider says why.
Every provider selling Qwen2.5 VL 72B Instruct
- 1
$0.25 in · $0.75 out · 32k context here
$0.38/M tokens - 2
$0.70 in · $0.70 out · 66k context here
$0.70/M tokens - 3
$0.80 in · $0.80 out · 33k context here
$0.80/M tokens - 4
$0.80 in · $0.80 out · 33k context here
$0.80/M tokens - 5
$0.80 in · $1 out
$0.85/M tokens - 6
$0.80 in · $1 out
$0.85/M tokens - 7
$0.80 in · $1 out
$0.85/M tokens - 8
$0.84 in · $1.06 out
$0.90/M tokens - 9
$1.01 in · $1.01 out · 33k context here
$1.01/M tokens - 10
$1.01 in · $1.01 out · 33k context here
$1.01/M tokens - 11
$1.02 in · $1.02 out · 32k context here
$1.02/M tokens - 12
$1.95 in · $8 out · 33k context here
$3.46/M tokens - 13
Qiniu
Costs more$2.32 in · $6.96 out
$3.48/M tokens
Not ranked
Below the maker's own price with nothing published to account for it, from a catalog we could not read reliably, or a free tier, which is a limit rather than a price. Why
$0.80 in · $1 out · 33k context here
$0.85/M tokens
What it costs for your work
A month at OpenRouter's own price
A month at Nebius Token Factory, the cheapest
What you save
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.
How we count
Prices are per million tokens. The big number on each row is blended 3 in : 1 out, the way most work uses a model. A price below OpenRouter's own is listed as cheapest only when the provider says why. Alibaba Cloud trained Qwen2.5 VL 72B Instruct and sells it on no catalog we read, so the price every row is measured against is OpenRouter's.
- Runs it themselves
- The provider runs the open weights on hardware of its own, so the price is its own rather than a resale.
- Resells
- The provider sells another company's endpoint, at a margin of its own or at the maker's price.
- Same as maker
- Sold by someone else at the price the maker charges.
- Costs more
- Sold by someone else for more than the maker charges.
- Not ranked
- Below the maker's price on a closed model with nothing to account for it, or from a catalog we could not read reliably. Listed, and never a pick.
Similar models
Models from other labs that do what Qwen2.5 VL 72B Instruct does, cheapest first. Each percentage is against Qwen2.5 VL 72B Instruct's cheapest price, $0.38 per M tokens.
Frequently asked
- Who sells Qwen2.5 VL 72B Instruct cheapest?
- Nebius Token Factory, at $0.25 in and $0.75 out per million tokens, checked 31 Oct 2026. The provider runs the open weights on hardware of its own, so the price is its own rather than a resale.
- Is Qwen2.5 VL 72B Instruct open weights?
- Yes. Alibaba Cloud publishes the weights, so anyone may host Qwen2.5 VL 72B Instruct, which is why 14 providers sell it and why their prices differ so much.
- How much context does Qwen2.5 VL 72B Instruct hold?
- 128,000 tokens in one call, which is about 128k.
- How does Qwen2.5 VL 72B Instruct compare with the rest of the market?
- At $0.85 per million tokens, OpenRouter's own price is 4% below the typical $0.88 across the 392 text models we track.
More from Alibaba Cloud