qwen-2.5-72b-instruct
completions
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).
Input:$0.1 / 1M tokens
Output:$0.1 / 1M tokens
Context:32768 tokens
text
text
Access qwen-2.5-72b-instruct through LangDB AI Gateway
Recommended
Integrate with qwen's qwen-2.5-72b-instruct and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.
Unified API
Cost Optimization
Enterprise Security
Get Started Now
Free tier available • No credit card required
Instant Setup
99.9% Uptime
10,000+Monthly Requests
Code Example
Configuration
Base URL
API Keys
Headers
Project ID in header
X-Run-Id
X-Thread-Id
Model Parameters
13 availablefrequency_penalty
-202
logit_bias
logprobs
max_tokens
min_p
001
presence_penalty
-201.999
repetition_penalty
012
seed
stop
temperature
012
top_k
top_logprobs
top_p
011
Additional Configuration
Tools
Guards
User:
Id:
Name:
Tags:
Publicly Shared Threads5
- 2 months agoExplains how Andrew has N+1 sisters by including Alice among the N sisters and considering family from Andrew's viewpoint.counting siblingsfamily relationshipssisters and brothers mathperspective on siblings
- 2 months agoTrains A and B meet at 11:17 AM, 137 km east of Station X, accounting for Train A's one-hour head start.train meeting time calculationrelative speed problemtrain head start distancetrain collision point calculation
- 2 months agoPython code implementing A* algorithm using Manhattan distance to find shortest path on a grid, returning path or empty list if none found.a* pathfinding pythonmanhattan distance heuristicgrid shortest pathpathfinding algorithm example
- Detailed 3-step weighing plan to find the single lighter counterfeit coin among 12 using 3 weighings, narrowing down groups each step.counterfeit coin problembalance scale puzzlethree weighings strategyidentify lighter fake coin
- 2 months agoSolved 3x + 5y = 100 by finding one solution (200, -100), deriving general form x=200+5k, y=-100-3k, then listing integer pairs with non-negative x,y.diophantine equation solutions3x plus 5y equals 100integer solutions to linear equationsgeneral solution diophantine
Popular Models10
deepseek-chat-v3-0324deepseekDeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well on a variety of tasks.Input:$0.25 / 1M tokensOutput:$0.85 / 1M tokensContext:163840 tokenstexttext- deepseek-r1-0528deepseekMay 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model.Input:$0.27 / 1M tokensOutput:$0.27 / 1M tokensContext:163840 tokenstexttext
- deepseek-chatdeepseekDeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations reveal that the model outperforms other open-source models and rivals leading closed-source models. For model details, please visit [the DeepSeek-V3 repo](https://github.com/deepseek-ai/DeepSeek-V3) for more information, or see the [launch announcement](https://api-docs.deepseek.com/news/news1226).Input:$0.27 / 1M tokensOutput:$0.27 / 1M tokensContext:163840 tokenstexttext
llama-guard-4-12bmeta-llamaLlama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM—generating text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated. Llama Guard 4 was aligned to safeguard against the standardized MLCommons hazards taxonomy and designed to support multimodal Llama 4 capabilities. Specifically, it combines features from previous Llama Guard models, providing content moderation for English and multiple supported languages, along with enhanced capabilities to handle mixed text-and-image prompts, including multiple images. Additionally, Llama Guard 4 is integrated into the Llama Moderations API, extending robust safety classification to text and images.Input:$0.05 / 1M tokensOutput:$0.05 / 1M tokensContext:163840 tokenstextimagetext- Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following, logical reasoning, math, code, and tool usage. The model supports a native 262K context length and does not implement "thinking mode" (<think> blocks). Compared to its base variant, this version delivers significant gains in knowledge coverage, long-context reasoning, coding benchmarks, and alignment with open-ended tasks. It is particularly strong on multilingual understanding, math reasoning (e.g., AIME, HMMT), and alignment evaluations like Arena-Hard and WritingBench.Input:$0.12 / 1M tokensOutput:$0.12 / 1M tokensContext:262144 tokenstexttext
claude-3.7-sonnetanthropicIntelligent model, with visible step‑by‑step reasoningInput:$3 / 1M tokensOutput:$15 / 1M tokensContext:200K tokenstoolstexttextimage
gpt-4o-miniopenaiGPT-4o mini (o for omni) is a fast, affordable small model for focused tasks. It accepts both text and image inputs, and produces text outputs (including Structured Outputs). It is ideal for fine-tuning, and model outputs from a larger model like GPT-4o can be distilled to GPT-4o-mini to produce similar results at lower cost and latency.The knowledge cutoff for GPT-4o-mini models is October, 2023.Input:$0.15 / 1M tokensOutput:$0.6 / 1M tokensContext:128K tokenstoolstextimagetext- deepseek-r1deepseekDeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model & [technical report](https://api-docs.deepseek.com/news/news250120). MIT licensed: Distill & commercialize freely!Input:$0.4 / 1M tokensOutput:$2 / 1M tokensContext:163840 tokenstexttext
- deepseek-reasonerdeepseekDeepSeek-Reasoner is an advanced AI model designed to enhance logical reasoning and problem-solving capabilities, leveraging deep learning techniques to provide accurate and contextually relevant insights across various domains.Input:$0.55 / 1M tokensOutput:$2.19 / 1M tokensContext:64K tokenstexttext
- claude-sonnet-4anthropicOur high-performance model with exceptional reasoning and efficiencyInput:$3 / 1M tokensOutput:$15 / 1M tokensContext:200K tokenstoolstextimagetext