LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen2.5-VL 72B Instruct

alibaba·alibaba/qwen2-5-vl-72b-instruct·GA·Open weights·qwen series
Qwen vision-language model for visual reasoning, documents, and agent tasks

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·NanoGPTGateway
$0.70 / $0.70
Blended $0.70 · 3.3× spread
Context
128,000
Output limit
8,192
Knowledge cutoff
2024-04
Released / updated
2025-01-26 / 2025-01-26
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideo
Weights
Hugging Face

Qwen2.5-VL 72B Instruct by alibaba is offered by 6 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is NanoGPT at $0.70 / $0.70 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 3.3× across the providers that host it.

The context window is 128,000 tokens at the reference host, but hosts report different limits, from 32,000 to 128,000, so the usable window depends on the provider you pick. It supports tool use and structured output. Accepted input modalities are Text, Image, and Video. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-04.

Available at 6 providers6 with public prices

  • ProviderInput / Output
  • NanoGPTGateway
    qwen/qwen2.5-vl-72b-instruct
    $0.70 / $0.70
    Cache read $0.35Context 32,000 ⚠Output limit 32,000
  • OpenRouterGateway
    qwen/qwen2.5-vl-72b-instruct
    $0.80 / $1.00
    Cache read $0.40Context 128,000Output limit 115,200
  • Kilo GatewayGateway
    qwen/qwen2.5-vl-72b-instruct
    $0.80 / $1.00
    Cache read $0.40Context 128,000Output limit 115,200
  • OVHcloud AI EndpointsCloud
    qwen2.5-vl-72b-instruct
    $1.01 / $1.01
    Context 32,768 ⚠Output limit 32,768
  • CortecsGateway
    qwen2.5-vl-72b-instruct
    $1.01 / $1.01
    Context 32,000 ⚠Output limit 32,000
  • QiniuGateway
    qwen2.5-vl-72b-instruct
    $2.32 / $6.96
    Context 128,000Output limit 8,192deprecated
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NanoGPT
qwen/qwen2.5-vl-72b-instruct
Gateway$0.70$0.70$0.35—32,000 ⚠32,000
OpenRouter
qwen/qwen2.5-vl-72b-instruct
Gateway$0.80$1.00$0.40—128,000115,200
Kilo Gateway
qwen/qwen2.5-vl-72b-instruct
Gateway$0.80$1.00$0.40—128,000115,200
OVHcloud AI Endpoints
qwen2.5-vl-72b-instruct
Cloud$1.01$1.01——32,768 ⚠32,768
Cortecs
qwen2.5-vl-72b-instruct
Gateway$1.01$1.01——32,000 ⚠32,000
Qiniu
qwen2.5-vl-72b-instruct
Gateway$2.32$6.96——128,0008,192deprecated

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

Common scenarios
1NanoGPT$132.98
2OpenRouter$162.00
3Kilo Gateway$162.00
4OVHcloud AI Endpoints$252.50
5Cortecs$253.50
6Qiniu$811.59
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$8.40$02026-08-052026-10-25
2026-10-25Input list —Output list —Min blended $0.70

Related models

Qwen4 Maxsame series—Qwen 3.6 Plus Uncensoredsame series—Qwen 3.8 27B Uncensoredsame series—Qwen-VL Maxsame lab$0.80 / $3.20Qwen2.5 7B Instructsame lab—
Data partly from models.dev (MIT)