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

For a chatbot handling 10,000 requests a day with 1,000 input and 500 output tokens each, Qwen2.5-VL 72B Instruct costs about $2,100 per month at Alibaba's list prices ($2.80 per 1M input tokens, $8.40 per 1M output tokens).

Does Qwen2.5-VL 72B Instruct support prompt caching?

No cache read price is published for Qwen2.5-VL 72B Instruct.

How long is Qwen2.5-VL 72B Instruct's context window?

Qwen2.5-VL 72B Instruct accepts up to 131,072 tokens (131K) of context and returns up to 8,192 tokens per response.

Qwen2.5-VL 72B Instruct API Pricing

Alibaba · released September 2024 · 131K context · API model ID qwen2-5-vl-72b-instruct

Qwen2.5-VL 72B Instruct by Alibaba API pricing: $2.80 per 1M input tokens and $8.40 per 1M output tokens (provider list price via models.dev, Oct 10, 2026).

Prices

Qwen2.5-VL 72B Instruct prices, USD per 1M tokens
Price	USD per 1M tokens
Input	$2.80
Output	$8.40
Cache read	Not published
Cache write	Not published

Alibaba's list price for its own API, as compiled by models.dev and checked Oct 10, 2026, 09:00 UTC. Prices on cloud platforms and resellers can differ. Provider documentation

Estimated monthly cost

$2,100

per month

per day: $70.00
per request: $0.007

Cost = input tokens × input price + output tokens × output price, 30 days a month. Cached input uses the cache read price. Cache write fees are not included.

Compare this workload across models

Monthly cost by workload

Workload	Per month
Chatbot1,000 in / 500 out tokens, 10,000 requests a day	$2,100/mo
RAG8,000 in / 500 out tokens, 5,000 requests a day	$3,990/mo
Coding agent50,000 in / 2,000 out tokens, 1,000 requests a day, 80% cached input	$4,704/mo

Context and capabilities

Context: 131,072 tokens
Max output: 8,192 tokens
Input: text, image
Output: text
Knowledge cutoff: April 2024
Open weights: Yes
Tool calling: Yes
Reasoning: No
Structured outputs: No

Capabilities and limits as listed by models.dev.

Similarly priced models

Claude Sonnet 5.5 · $2.00 in / $10.00 out
GPT-6.1 Sol · $2.00 in / $10.00 out
Gemini 3.1 Pro Preview · $2.00 in / $12.00 out
Qwen3.8 Max · $2.00 in / $6.00 out

Price history

No price changes since we started tracking on Oct 8, 2026.

Questions

How much does Qwen2.5-VL 72B Instruct cost per month?: For a chatbot handling 10,000 requests a day with 1,000 input and 500 output tokens each, Qwen2.5-VL 72B Instruct costs about $2,100 per month at Alibaba's list prices ($2.80 per 1M input tokens, $8.40 per 1M output tokens).
Does Qwen2.5-VL 72B Instruct support prompt caching?: No cache read price is published for Qwen2.5-VL 72B Instruct.
How long is Qwen2.5-VL 72B Instruct's context window?: Qwen2.5-VL 72B Instruct accepts up to 131,072 tokens (131K) of context and returns up to 8,192 tokens per response.