Qwen

Qwen2.5 72B Instruct API Pricing 2026

Compare pricing, benchmarks, and providers for Qwen2.5 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 72B Instruct was released on September 19, 2024. Pricing starts at $0.288 per million input tokens and $0.320 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$0.288
Output$0.320
Cached$0.450
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
Tools

Qwen2.5 72B Instruct is priced at $0.288 per million input tokens and $0.320 per million output tokens. It has a context window of 32,768 tokens. It is available from 5 providers, with DeepInfra the cheapest at $0.288 per million input tokens (input prices range from $0.288 to $1.20). On benchmarks, Qwen2.5 72B Instruct scores Aider 65.4 (63rd percentile). Over the past ~90 days its cheapest input price has fallen 20%, from $0.360 to $0.288 per million tokens.

Pricing Comparison

Compare Qwen2.5 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
$0.288
$0.320
—
—
—
32,768
Try
$0.250
$1.500
—
—
82.2
1,048,576
Try
$0.260
$0.780
—
—
—
1,000,000
Try
$0.260
$0.780
—
—
—
1,000,000
Try
$0.260
$1.560
—
—
—
1,000,000
Try
$0.260
$0.900
—
—
—
262,144
Try
$0.270
$0.950
—
—
—
196,608
Try
$0.270
$0.400
—
—
—
163,840
Try
$0.270
$0.410
—
—
—
163,840
Try
$0.270
$1.000
—
—
—
163,840
Try
$0.285
$0.950
—
—
—
1,048,576
Try

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

Compare Providers

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

5
Providers
$0.288
Cheapest Input/M
$0.320
Cheapest Output/M
DeepInfra
Best Price

Provider Pricing

5 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
DeepInfra
DeepInfra
Best Price
$0.288
$0.320
-
-
-
$0.360
$0.400
-
-
-
$0.380
$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 72B Instruct perform? Vote based on your experience.

Cost vs. Quality

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

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

Try Qwen2.5 72B Instruct

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

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

Open Playground

Frequently Asked Questions

Qwen2.5 72B Instruct costs $0.000288 per 1,000 input tokens and $0.000320 per 1,000 output tokens.
Qwen2.5 72B Instruct is available from 5 providers. DeepInfra offers the best price.
DeepInfra offers Qwen2.5 72B Instruct at $0.288 per million input tokens, the lowest of 5 providers (input prices range from $0.288 to $1.20 per million tokens).
Qwen2.5 72B Instruct scores Aider 65.4 (63rd percentile). Only benchmarks with published data for this model are shown.
Yes. Over the past ~90 days, the cheapest input price for Qwen2.5 72B Instruct has dropped 20%, from $0.360 to $0.288 per million tokens.
We compare Qwen2.5 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 →