Author's Description
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](https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE).
Key Specifications
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
Performance Summary
Qwen2.5 72B Instruct, created on September 18, 2024, demonstrates strong overall performance. It consistently ranks among the fastest models, achieving an Infinityth percentile in speed across seven benchmarks. In terms of cost, it typically provides cost-effective solutions, ranking in the 65th percentile across six benchmarks. The model exhibits exceptional reliability with a 99% success rate across seven benchmarks, indicating minimal technical failures. Analysis of benchmark results reveals several strengths. Qwen2.5 72B achieved perfect accuracy in the Ethics (Baseline) benchmark, also standing out as the most accurate model at its price point and among models of comparable speed. It demonstrated very high accuracy in General Knowledge (99.5%) and strong performance in Email Classification (98.0%). The model shows improved capabilities in coding (85.0% accuracy) and mathematics, aligning with its description of specialized expert models in these domains. While one Instruction Following benchmark showed 0.0% accuracy, another achieved a respectable 67.0%, suggesting some variability or specific challenge in the former. Its performance in Reasoning (67.3%) indicates solid analytical capabilities. The model's described improvements in instruction following, long text generation, and structured data understanding are partially reflected in its benchmark results, though the 0% instruction following score warrants further investigation.
Model Pricing
Current Pricing
Feature | Price (per 1M tokens) |
---|---|
Prompt | $0.12 |
Completion | $0.39 |
Price History
Available Endpoints
Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
---|---|---|---|---|
DeepInfra
|
DeepInfra | qwen/qwen-2.5-72b-instruct | 32K | $0.12 / 1M tokens | $0.39 / 1M tokens |
Nebius
|
Nebius | qwen/qwen-2.5-72b-instruct | 131K | $0.13 / 1M tokens | $0.4 / 1M tokens |
Novita
|
Novita | qwen/qwen-2.5-72b-instruct | 32K | $0.38 / 1M tokens | $0.4 / 1M tokens |
Hyperbolic
|
Hyperbolic | qwen/qwen-2.5-72b-instruct | 131K | $0.4 / 1M tokens | $0.4 / 1M tokens |
Fireworks
|
Fireworks | qwen/qwen-2.5-72b-instruct | 32K | $0.0666 / 1M tokens | $0.267 / 1M tokens |
Together
|
Together | qwen/qwen-2.5-72b-instruct | 131K | $1.2 / 1M tokens | $1.2 / 1M tokens |
Chutes
|
Chutes | qwen/qwen-2.5-72b-instruct | 32K | $0.0666 / 1M tokens | $0.267 / 1M tokens |
NextBit
|
NextBit | qwen/qwen-2.5-72b-instruct | 65K | $0.0666 / 1M tokens | $0.267 / 1M tokens |
Benchmark Results
Benchmark | Category | Reasoning | Free | Executions | Accuracy | Cost | Duration |
---|
Other Models by qwen
|
Released | Params | Context |
|
Speed | Ability | Cost |
---|---|---|---|---|---|---|---|
Qwen: Qwen3 30B A3B Instruct 2507 | Jul 29, 2025 | 30B | 131K |
Text input
Text output
|
★★★★ | ★★★★ | $$$ |
Qwen: Qwen3 235B A22B Thinking 2507 | Jul 25, 2025 | 235B | 131K |
Text input
Text output
|
★ | ★★★★ | $$$$$ |
Qwen: Qwen3 Coder | Jul 22, 2025 | 480B | 1M |
Text input
Text output
|
★★★★ | ★★★ | $$$ |
Qwen: Qwen3 235B A22B Instruct 2507 | Jul 21, 2025 | 235B | 262K |
Text input
Text output
|
★ | ★★★ | $$$ |
Qwen: Qwen3 30B A3B | Apr 28, 2025 | 30B | 40K |
Text input
Text output
|
★ | ★★★★★ | $$$$ |
Qwen: Qwen3 8B | Apr 28, 2025 | 8B | 128K |
Text input
Text output
|
★ | ★★★ | $$$ |
Qwen: Qwen3 14B | Apr 28, 2025 | 14B | 40K |
Text input
Text output
|
★★ | ★★★★★ | $$$ |
Qwen: Qwen3 32B | Apr 28, 2025 | 32B | 40K |
Text input
Text output
|
★ | ★★★★★ | $$$ |
Qwen: Qwen3 235B A22B | Apr 28, 2025 | 235B | 40K |
Text input
Text output
|
★ | ★★★★ | $$$$ |
Qwen: Qwen2.5 VL 32B Instruct | Mar 24, 2025 | 32B | 128K |
Text input
Image input
Text output
|
★★ | ★★★ | $$$ |
Qwen: QwQ 32B | Mar 05, 2025 | 32B | 131K |
Text input
Text output
|
★ | ★★★ | $$$ |
Qwen: Qwen VL Plus | Feb 04, 2025 | — | 7K |
Text input
Image input
Text output
|
★★★★ | ★★ | $$$ |
Qwen: Qwen VL Max | Feb 01, 2025 | — | 7K |
Text input
Image input
Text output
|
★★★★★ | ★★★ | $$$$ |
Qwen: Qwen-Turbo | Feb 01, 2025 | — | 1M |
Text input
Text output
|
★★★★★ | ★★★★ | $$ |
Qwen: Qwen2.5 VL 72B Instruct | Feb 01, 2025 | 72B | 32K |
Text input
Image input
Text output
|
★★★★ | ★★★★ | $$ |
Qwen: Qwen-Plus | Feb 01, 2025 | — | 131K |
Text input
Text output
|
★★★ | ★★★★ | $$$ |
Qwen: Qwen-Max | Feb 01, 2025 | — | 32K |
Text input
Text output
|
★★★ | ★★★★ | $$$$ |
Qwen: QwQ 32B Preview | Nov 27, 2024 | 32B | 32K |
Text input
Text output
|
— | ★ | $$ |
Qwen2.5 Coder 32B Instruct | Nov 11, 2024 | ~500B | 32K |
Text input
Text output
|
★★★★★ | ★★★★★ | $ |
Qwen2.5 7B Instruct | Oct 15, 2024 | ~500B | 32K |
Text input
Text output
|
★ | ★★★ | $$ |
Qwen: Qwen2.5-VL 7B Instruct | Aug 27, 2024 | ~500B | 32K |
Text input
Image input
Text output
|
★★★ | ★★★ | $$$ |
Qwen 2 72B Instruct | Jun 06, 2024 | ~500B | 32K |
Text input
Text output
|
★★★★ | ★★ | $$$$ |