What is Qwen2.5 72B Instruct?

Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains.

How much does Qwen2.5 72B Instruct cost?

Qwen2.5 72B Instruct costs $0.36/M input tokens and $0.40/M output tokens.

What is the context length of Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct has a 32,768 token context window. It supports up to 16,384 completion tokens.

Does Qwen2.5 72B Instruct support tool calling and structured outputs?

Yes. Qwen2.5 72B Instruct accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Which providers serve Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct is served by 1 provider on OpenRouter: DeepInfra.

What other text models does Qwen have?

Qwen3.8 Max Prime, Qwen3.8 Omni Flash, Qwen3.8 Max (0902) and 36 more are other text models from Qwen.

When was Qwen2.5 72B Instruct released?

Qwen2.5 72B Instruct was released on September 19, 2024. Its knowledge cutoff is June 30, 2024.

Qwen2.5 72B Instruct

qwen/qwen-2.5-72b-instruct

Model weights

Compare

Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2:

Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains.
Significant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots.
Long-context Support up to 128K tokens and can generate up to 8K tokens.
Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.

Usage of this model is subject to Tongyi Qianwen LICENSE AGREEMENT.

Modalities

In / out price

$0.36 / $0.40per 1M

Context

33K

Released

Sep 19, 2024

Knowledge cutoff

Jun 2024

Providers

This model is hosted by one provider. OpenRouter forwards every request without routing.

Latency / throughput


	$0.36	$0.40	0.36s	42 tok/s	99.48%

Input $0.36Output $0.40
42 tok/s99.48% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.3596/M tokens

Output

$0.3986/M tokens

Qwen2.5 72B Instruct — Price history

Price history

No effective price data for this selection

		$0.360	$0.399	0.0%	100.0%

Effective in $0.360Effective out $0.399
Token share
100.0%

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.53%

Availability over the last 3 days

Last 72 hours

Availability 99.53%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.91%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Qwen2.5 72B Instruct (Artificial Analysis)
Source	Benchmark	Score
Artificial Analysis	Qwen2.5 Instruct 72B GPQA Diamond	49.1%
Artificial Analysis	Qwen2.5 Instruct 72B HLE	3.6%
Artificial Analysis	Qwen2.5 Instruct 72B IFBench	36.9%
Artificial Analysis	Qwen2.5 Instruct 72B τ²-Bench Telecom	34.5%
Artificial Analysis	Qwen2.5 Instruct 72B CritPt	0.0%
Artificial Analysis	Qwen2.5 Instruct 72B LiveCodeBench	27.6%
Artificial Analysis	Qwen2.5 Instruct 72B Terminal-Bench Hard	4.5%
Artificial Analysis	Qwen2.5 Instruct 72B MMLU-Pro	72.0%
Artificial Analysis	Qwen2.5 Instruct 72B AIME 2025	14.0%
Artificial Analysis	Qwen2.5 Instruct 72B AIME	16.0%
Artificial Analysis	Qwen2.5 Instruct 72B MATH-500	85.8%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Stockteller Intelligence

new

425Mtokens

Fraction AI

Large perpetual datasets with community ownership

166Mtokens

Troven LLM Analysis

new

98.2Mtokens

G0DM0D3-pliny

new

96.8Mtokens

OpenClaw

OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.

80.6Mtokens

Rest of OpenRouter

41.8M

Top 5 Apps

9.15M

Not currently available through EU in-region routing. In-region routing docs

More models from Qwen

Qwen Image 2.1 Turbo

Qwen Image 2.1 Turbo is the fast, lower-cost tier of the Qwen Image 2.1 series from Qwen, for image generation and editing where throughput and price matter more than peak fidelity. See Qwen Image 2.1 Pro for the higher-quality tier.

Imagefrom $0.0184/image

Qwen Image 2.1 Pro

Qwen Image 2.1 Pro is an image generation and editing model from Qwen, the higher-quality tier of the Qwen Image 2.1 series. Choose it over Qwen Image 2.1 Turbo when output fidelity matters more than cost or speed.

Imagefrom $0.046/image

Qwen3.8 Max Prime

Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default. Tool calling, structured outputs, and configurable reasoning effort are supported, matching Qwen3.8 Max.

Text1M context$4 / $12

Qwen3.8 Omni Flash

Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization, video editing and production workflows, audio-video dialogue, coding, knowledge work, and GUI interaction, and it is particularly strong at long-form multimedia tasks that combine speech, sound, and visual context. It also supports two-channel and four-channel spatial audio understanding.

Text1M context$0.15 / $0.47

Qwen3.8 Max

Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default.

This snapshot is post-trained for coding and agentic work, including multi-step software projects, multi-tool orchestration, and long-horizon task execution. It also targets chart reasoning, document parsing, and multimodal understanding over long documents and extended video. Tool calling, structured outputs, and configurable reasoning effort are supported.

Text1M context$2 / $6

Qwen3.8 Max (batch)

Text262K context$1.15 / $3.45

Qwen3.8 Flash

Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.

Text1M context$0.15 / $0.47

Qwen3 Reranker 0.6B

Qwen3 Reranker 0.6B is the smallest text reranking model from Alibaba Cloud in the Qwen3 Reranker series. Built on the Qwen3 architecture, it evaluates query-document pairs to produce relevance scores for retrieval and RAG pipelines. Supports 100+ languages with instruction-aware reranking. Designed for low-latency, resource-constrained deployments.

Rerank$0.20/M tokens

Qwen3 Reranker 4B

Qwen3 Reranker 4B is a text reranking model from Alibaba Cloud built on the Qwen3 architecture. It evaluates query-document pairs to produce relevance scores for use in retrieval and RAG pipelines. Supports 100+ languages and programming languages, with instruction-aware reranking that allows customizing scoring criteria per task. A compact 4B alternative balancing performance and inference cost.

Rerank

Qwen3.8 27B

Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be enabled or disabled.

Text1.0M context$0.035 / $1.50

Qwen3.8 27B (batch)

Text262K context$0.16 / $2

Qwen3 Reranker 8B

Qwen3 Reranker 8B is a text reranking model from Alibaba Cloud built on the Qwen3 architecture. It evaluates query-document pairs to produce relevance scores for use in retrieval and RAG pipelines. Supports 100+ languages and programming languages, with instruction-aware reranking that allows customizing scoring criteria per task. Offers strong performance on multilingual benchmarks including MTEB, CMTEB, and MMTEB.

Rerank$0.20/M tokens

Qwen3 ASR 1.7B

Qwen3 ASR 1.7B is an automatic speech recognition model from Qwen. It supports multilingual language identification and transcription across 30 languages and 22 Chinese dialects, with streaming and offline inference plus segment-level and word-level timestamps.

Transcription$0.000008/second

Qwen3 ASR 0.6B

Qwen3 ASR 0.6B is a compact automatic speech recognition model from Qwen. It supports multilingual language identification and transcription across 30 languages and 22 Chinese dialects, with streaming and offline inference plus segment-level and word-level timestamps.

Transcription$0.000003/second

Qwen3.8 2.4T A95B

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is suited for coding, research, complex reasoning, and agentic workflows.

Text1.0M context$2 / $6

Qwen Image 3 Pro

Qwen Image 3 Pro is an image generation and editing model from Qwen. It supports precise rendering of text and details as small as 10px, along with richer world knowledge compared to previous generations.

Imagefrom $0.04/image

Qwen Image 3

Qwen Image 3 is a unified image generation and editing model from Qwen. It supports precise rendering of text and details as small as 10px, along with a richer world knowledge base than previous generations.

Imagefrom $0.03/image

Qwen3.8 Max

Qwen3.8 Max (0803) is the August 3, 2026 checkpoint of Qwen3.8 Max, the flagship model in Alibaba's Qwen3.8 series and the general-availability successor to the Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning, visual understanding, coding, and agentic workflows. This checkpoint was superseded by Qwen3.8 Max (0902) on September 5, 2026.

Text1M context

Qwen3.7 Flash

Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world visual perception.

Text1M context$0.03 / $0.13

Qwen-Audio-3.0-TTS Flash

Qwen-Audio-3.0-TTS Flash is Alibaba's fast, cost-efficient text-to-speech model, generating spoken audio from text via the DashScope Speech Synthesizer API.

Speech$15/M characters

Qwen2.5 72B Instruct

Providers

Pricing

Weighted average

Qwen2.5 72B Instruct — Price history

Performance

Uptime

Availability over the last 3 days

Availability over the last 24 hours

Benchmarks

Apps

Activity

API

Frequently asked questions

Explore more models

More models from Qwen

More models from Qwen