Qwen2.5 72B Instruct API Pricing 2026

Overview

Qwen2.5 72B Instruct was released on September 19, 2024. Pricing starts at $0.120 per million input tokens and $0.390 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$0.120

Output$0.390

per 1M tokens

Speed

Output47 tok/s

TTFT1.08s

median latency

Capabilities

Tools

Pricing Comparison

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

Current Pricing (per 1M tokens)

11 models

Provider	Model	Input $/M	Output $/M	Context	Actions
QW Qwen	qwen-2.5-72b-instruct	$0.120	$0.390	32,768	Try
OG Opengvlab	internvl3-78b	$0.100	$0.390	32,768	Try
O OpenAI	gpt-4.1-nano	$0.100	$0.400	1,047,576	Try
G Google	gemini-2.0-flash-001	$0.100	$0.400	1,048,576	Try
M Meta-llama	llama-3.3-70b-instruct	$0.100	$0.320	131,072	Try
MI Mistral AI	ministral-8b	$0.100	$0.100	131,072	Try
MI Mistral AI	pixtral-12b	$0.100	$0.100	32,768	Try
QW Qwen	qwen3-235b-a22b-thinking-2507	$0.110	$0.600	262,144	Try
NO Nousresearch	hermes-4-70b	$0.110	$0.380	131,072	Try
MI Mistral AI	mistral-7b-instruct-v0.1	$0.110	$0.190	2,824	Try
A Allenai	olmo-3-7b-think	$0.120	$0.200	65,536	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.

6

Providers

$0.070

Cheapest Input/M

$0.260

Cheapest Output/M

OpenRouter

Best Price

Provider Pricing

6 models

Provider	Input $/M	Output $/M	Uptime
OpenRouter Best Price	$0.070	$0.260	-
D DeepInfra	$0.120	$0.390	100.0%
C Chutes	$0.130	$0.520	-
N Novita	$0.380	$0.400	100.0%
H Hyperbolic	$0.400	$0.400	100.0%
T Together	$1.200	$1.200	-

Provider pricing data sourced from OpenRouter and Helicone

Cost vs. Quality

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

X-axis:

Y-axis:

Loading chart...

Qwen2.5 72B Instruct

Other models

Detailed Benchmark Scores

Intelligence

15.6 (41th pct)

Coding

11.8 (30th pct)

Math

14.0 (18th pct)

MMLU Pro

72.0 (46th pct)

GPQA

49.1 (38th pct)

LiveCodeBench

27.6 (30th pct)

AIME

16.0 (38th pct)

Aider

65.4 (61th pct)

Benchmark data from Artificial Analysis and HuggingFace Open LLM Leaderboard

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