Qwen

Qwen2.5 VL 72B Instruct API Pricing 2026

Compare pricing, benchmarks, and providers for Qwen2.5 VL 72B Instruct. Find the best value for your use case.

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

Qwen2.5 VL 72B Instruct was released on February 1, 2025. Pricing starts at $0.800 per million input tokens and $0.900 per million output tokens. The model supports a context window of up to 33K tokens. API access is available through Qwen.

Context Window
33K
tokens
Pricing
Input$0.800
Output$0.900
Cached$0.400
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
VisionToolsCaching

Qwen2.5 VL 72B Instruct is priced at $0.800 per million input tokens and $0.900 per million output tokens. It has a context window of 32,768 tokens. It is available from 4 providers, with Parasail the cheapest at $0.800 per million input tokens (input prices range from $0.800 to $1.20). Over the past ~90 days its cheapest input price has risen 220%, from $0.250 to $0.800 per million tokens.

Pricing Comparison

Compare Qwen2.5 VL 72B Instruct with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$0.800
$0.900
—
—
—
32,768
Try
$0.750
$3.750
—
—
95.3
1,048,576
Try
$0.776
$0.776
—
—
—
16,384
Try
$0.780
$3.900
—
—
—
262,144
Try
$0.780
$3.900
—
—
—
262,144
Try
$0.800
$2.400
—
—
—
-
Try
$0.800
$1.200
—
—
—
81,920
Try
$0.800
$1.600
—
—
—
32,768
Try
$0.800
$4.000
—
—
—
200,000
Try
$0.800
$0.800
—
—
—
16,384
Try
$0.800
$1.200
—
—
—
4,096
Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

Qwen2.5 VL 72B Instruct is available from multiple providers with different pricing and availability.

4
Providers
$0.800
Cheapest Input/M
$0.900
Cheapest Output/M
Parasail
Best Price

Provider Pricing

4 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Input $/M
Output $/M
Cache Read $/M
Cache Write $/M
Uptime
Parasail
Parasail
Best Price
$0.800
$1.000
$0.400
-
100.0%
OpenRouter
OpenRouter
Best Price
$0.800
$1.000
$0.400
-
-
$0.900
$0.900
$0.450
-
-
$1.200
$1.200
-
-
-
Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does Qwen2.5 VL 72B Instruct perform? Vote based on your experience.

Cost vs. Quality

Compare Qwen2.5 VL 72B Instruct's benchmark performance against all models.

X-axis:
Y-axis:
Loading chart...
Other models

Try Qwen2.5 VL 72B Instruct

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Qwen2.5 VL 72B Instruct directly in your browser.

Open Playground

Frequently Asked Questions

Qwen2.5 VL 72B Instruct costs $0.000800 per 1,000 input tokens and $0.000900 per 1,000 output tokens.
Qwen2.5 VL 72B Instruct is available from 4 providers. Parasail offers the best price.
Parasail offers Qwen2.5 VL 72B Instruct at $0.800 per million input tokens, the lowest of 4 providers (input prices range from $0.800 to $1.20 per million tokens).
Yes. Over the past ~90 days, the cheapest input price for Qwen2.5 VL 72B Instruct has increased 220%, from $0.250 to $0.800 per million tokens.
We compare Qwen2.5 VL 72B Instruct with 10 similarly-priced models. See the benchmark scatter plot above to compare quality vs cost.

All Qwen Models

See pricing for all Qwen models.

View all Qwen models →