List of All LLM Models
Discover and compare 500+ large language models with real-time rankings, benchmarks, and community votes.
Tongyi DeepResearch 30B A3B
By alibaba
Tongyi DeepResearch is an agentic large language model developed by Tongyi Lab, with 30 billion total parameters activating only 3 billion per token. It's optimized for long-horizon, deep information-seeking tasks and delivers state-of-the-art performance on benchmarks like Humanity's Last Exam, BrowserComp, BrowserComp-ZH, WebWalkerQA, GAIA, xbench-DeepSearch, and FRAMES. This makes it superior for complex agentic search, reasoning, and multi-step problem-solving compared to prior models. The model includes a fully automated synthetic data pipeline for scalable pre-training, fine-tuning, and reinforcement learning. It uses large-scale continual pre-training on diverse agentic data to boost reasoning and stay fresh. It also features end-to-end on-policy RL with a customized Group Relative Policy Optimization, including token-level gradients and negative sample filtering for stable training. The model supports ReAct for core ability checks and an IterResearch-based 'Heavy' mode for max performance through test-time scaling. It's ideal for advanced research agents, tool use, and heavy inference workflows.
Release Date
18 Sep 2025
Context Size
131.07K
Qwen: Qwen3 Coder Flash
By Qwen
Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling and environment interaction, combining coding proficiency with versatile general-purpose abilities.
Release Date
17 Sep 2025
Context Size
1M
Arcee AI: AFM 4.5B
By arcee-ai
AFM-4.5B is a 4.5 billion parameter instruction-tuned language model developed by Arcee AI. The model was pretrained on approximately 8 trillion tokens, including 6.5 trillion tokens of general data and 1.5 trillion tokens with an emphasis on mathematical reasoning and code generation.
Release Date
16 Sep 2025
Context Size
65.54K
OpenGVLab: InternVL3 78B
By opengvlab
The InternVL3 series is an advanced multimodal large language model (MLLM). Compared to InternVL 2.5, InternVL3 demonstrates stronger multimodal perception and reasoning capabilities. In addition, InternVL3 is benchmarked against the Qwen2.5 Chat models, whose pre-trained base models serve as the initialization for its language component. Benefiting from Native Multimodal Pre-Training, the InternVL3 series surpasses the Qwen2.5 series in overall text performance.
Release Date
15 Sep 2025
Context Size
0
Qwen: Qwen3 Next 80B A3B Thinking
By Qwen
Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic planning, and reports strong results across knowledge, reasoning, coding, alignment, and multilingual evaluations. Compared with prior Qwen3 variants, it emphasizes stability under long chains of thought and efficient scaling during inference, and it is tuned to follow complex instructions while reducing repetitive or off-task behavior. The model is suitable for agent frameworks and tool use (function calling), retrieval-heavy workflows, and standardized benchmarking where step-by-step solutions are required. It supports long, detailed completions and leverages throughput-oriented techniques (e.g., multi-token prediction) for faster generation. Note that it operates in thinking-only mode.
Release Date
11 Sep 2025
Context Size
131.07K
Qwen: Qwen3 Next 80B A3B Instruct (free)
By Qwen
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual use, while remaining robust on alignment and formatting. Compared with prior Qwen3 instruct variants, it focuses on higher throughput and stability on ultra-long inputs and multi-turn dialogues, making it well-suited for RAG, tool use, and agentic workflows that require consistent final answers rather than visible chain-of-thought. The model employs scaling-efficient training and decoding to improve parameter efficiency and inference speed, and has been validated on a broad set of public benchmarks where it reaches or approaches larger Qwen3 systems in several categories while outperforming earlier mid-sized baselines. It is best used as a general assistant, code helper, and long-context task solver in production settings where deterministic, instruction-following outputs are preferred.
Release Date
11 Sep 2025
Context Size
262.14K
Qwen: Qwen3 Next 80B A3B Instruct (free)
By qwen
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...
Release Date
11 Sep 2025
Context Size
262.14K
Meituan: LongCat Flash Chat
By meituan
LongCat-Flash-Chat is a large-scale Mixture-of-Experts (MoE) model with 560B total parameters, of which 18.6B–31.3B (≈27B on average) are dynamically activated per input. It introduces a shortcut-connected MoE design to reduce communication overhead and achieve high throughput while maintaining training stability through advanced scaling strategies such as hyperparameter transfer, deterministic computation, and multi-stage optimization. This release, LongCat-Flash-Chat, is a non-thinking foundation model optimized for conversational and agentic tasks. It supports long context windows up to 128K tokens and shows competitive performance across reasoning, coding, instruction following, and domain benchmarks, with particular strengths in tool use and complex multi-step interactions.
Release Date
09 Sep 2025
Context Size
131.07K
Qwen: Qwen Plus 0728 (thinking)
By Qwen
Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.
Release Date
08 Sep 2025
Context Size
1M
Qwen: Qwen Plus 0728 (thinking)
By qwen
Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.
Release Date
08 Sep 2025
Context Size
1M
NVIDIA: Nemotron Nano 9B V2
By Nvidia
NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. The model's reasoning capabilities can be controlled via a system prompt. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so.
Release Date
05 Sep 2025
Context Size
131.07K
NVIDIA: Nemotron Nano 9B V2 (free)
By nvidia
NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...
Release Date
05 Sep 2025
Context Size
128K
Sonoma Dusk Alpha
By OpenRouter
This is a cloaked model provided to the community to gather feedback. A fast and intelligent general-purpose frontier model with a 2 million token context window. Supports image inputs and parallel tool calling. Note: It’s free to use during this testing period, and prompts and completions are logged by the model creator for feedback and training.
Release Date
05 Sep 2025
Context Size
2M
Sonoma Sky Alpha
By OpenRouter
This is a cloaked model provided to the community to gather feedback. A maximally intelligent general-purpose frontier model with a 2 million token context window. Supports image inputs and parallel tool calling. Note: It’s free to use during this testing period, and prompts and completions are logged by the model creator for feedback and training.
Release Date
05 Sep 2025
Context Size
2M
MoonshotAI: Kimi K2 0905
By moonshotai
Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It supports long-context inference up to 256k tokens, extended from the previous 128k. This update improves agentic coding with higher accuracy and better generalization across scaffolds, and enhances frontend coding with more aesthetic and functional outputs for web, 3D, and related tasks. Kimi K2 is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. It excels across coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) benchmarks. The model is trained with a novel stack incorporating the MuonClip optimizer for stable large-scale MoE training.
Release Date
04 Sep 2025
Context Size
262.14K
ByteDance: Seed OSS 36B Instruct
By bytedance
Seed-OSS-36B-Instruct is a 36B-parameter instruction-tuned reasoning language model from ByteDance’s Seed team, released under Apache-2.0. The model is optimized for general instruction following with strong performance in reasoning, mathematics, coding, tool use/agentic workflows, and multilingual tasks, and is intended for international (i18n) use cases. It is not currently possible to control the reasoning effort.
Release Date
02 Sep 2025
Context Size
131.07K
Deep Cogito: Cogito V2 Preview Llama 70B
By deepcogito
Cogito v2 70B is a dense hybrid reasoning model that combines direct answering capabilities with advanced self-reflection. Built with iterative policy improvement, it delivers strong performance across reasoning tasks while maintaining efficiency through shorter reasoning chains and improved intuition.
Release Date
02 Sep 2025
Context Size
131.07K
Cogito V2 Preview Llama 109B
By deepcogito
An instruction-tuned, hybrid-reasoning Mixture-of-Experts model built on Llama-4-Scout-17B-16E. Cogito v2 can answer directly or engage an extended “thinking” phase, with alignment guided by Iterated Distillation & Amplification (IDA). It targets coding, STEM, instruction following, and general helpfulness, with stronger multilingual, tool-calling, and reasoning performance than size-equivalent baselines. The model supports long-context use (up to 10M tokens) and standard Transformers workflows. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)
Release Date
02 Sep 2025
Context Size
131.07K
Deep Cogito: Cogito V2 Preview Deepseek 671B
By deepcogito
Cogito v2 is a multilingual, instruction-tuned Mixture of Experts (MoE) large language model with 671 billion parameters. It supports both standard and reasoning-based generation modes. The model introduces hybrid reasoning via Iterated Distillation and Amplification (IDA)—an iterative self-improvement strategy designed to scale alignment with general intelligence. Cogito v2 has been optimized for STEM, programming, instruction following, and tool use. It supports 128k context length and offers strong performance in both multilingual and code-heavy environments. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)
Release Date
02 Sep 2025
Context Size
131.07K
StepFun: Step3
By stepfun-ai
Step3 is a cutting-edge multimodal reasoning model—built on a Mixture-of-Experts architecture with 321B total parameters and 38B active. It is designed end-to-end to minimize decoding costs while delivering top-tier performance in vision–language reasoning. Through the co-design of Multi-Matrix Factorization Attention (MFA) and Attention-FFN Disaggregation (AFD), Step3 maintains exceptional efficiency across both flagship and low-end accelerators.
Release Date
28 Aug 2025
Context Size
65.54K
Qwen: Qwen3 30B A3B Thinking 2507
By Qwen
Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated from final answers. Compared to earlier Qwen3-30B releases, this version improves performance across logical reasoning, mathematics, science, coding, and multilingual benchmarks. It also demonstrates stronger instruction following, tool use, and alignment with human preferences. With higher reasoning efficiency and extended output budgets, it is best suited for advanced research, competitive problem solving, and agentic applications requiring structured long-context reasoning.
Release Date
28 Aug 2025
Context Size
131.07K
xAI: Grok Code Fast 1
By xAI
Grok Code Fast 1 is a speedy and economical reasoning model that excels at agentic coding. With reasoning traces visible in the response, developers can steer Grok Code for high-quality work flows.
Release Date
26 Aug 2025
Context Size
256K
Nous: Hermes 4 70B
By Nous Research
Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either respond directly or generate explicit <think>...</think> reasoning traces before answering. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config) This 70B variant is trained with the expanded post-training corpus (~60B tokens) emphasizing verified reasoning data, leading to improvements in mathematics, coding, STEM, logic, and structured outputs while maintaining general assistant performance. It supports JSON mode, schema adherence, function calling, and tool use, and is designed for greater steerability with reduced refusal rates.
Release Date
26 Aug 2025
Context Size
131.07K
Nous: Hermes 4 405B
By Nous Research
Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with <think>...</think> traces or respond directly, offering flexibility between speed and depth. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config) The model is instruction-tuned with an expanded post-training corpus (~60B tokens) emphasizing reasoning traces, improving performance in math, code, STEM, and logical reasoning, while retaining broad assistant utility. It also supports structured outputs, including JSON mode, schema adherence, function calling, and tool use. Hermes 4 is trained for steerability, lower refusal rates, and alignment toward neutral, user-directed behavior.
Release Date
26 Aug 2025
Context Size
131.07K
Google: Gemini 2.5 Flash Image Preview (Nano Banana)
By Google
Gemini 2.5 Flash Image Preview, a.k.a. "Nano Banana," is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, and multi-turn conversations.
Release Date
26 Aug 2025
Context Size
32.77K
DeepSeek: DeepSeek V3.1
By DeepSeek
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config) The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. It succeeds the [DeepSeek V3-0324](/deepseek/deepseek-chat-v3-0324) model and performs well on a variety of tasks.
Release Date
21 Aug 2025
Context Size
32.77K
DeepSeek: DeepSeek V3.1 Base
By DeepSeek
This is a base model, trained only for raw next-token prediction. Unlike instruct/chat models, it has not been fine-tuned to follow user instructions. Prompts need to be written more like training text or examples rather than simple requests (e.g., “Translate the following sentence…” instead of just “Translate this”). DeepSeek-V3.1 Base is a 671B parameter open Mixture-of-Experts (MoE) language model with 37B active parameters per forward pass and a context length of 128K tokens. Trained on 14.8T tokens using FP8 mixed precision, it achieves high training efficiency and stability, with strong performance across language, reasoning, math, and coding tasks.
Release Date
20 Aug 2025
Context Size
163.84K
OpenAI: GPT-4o Audio
By OpenAI
The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user experiences. Audio outputs are currently not supported. Audio tokens are priced at $40 per million input and $80 per million output audio tokens.
Release Date
15 Aug 2025
Context Size
128K
Mistral: Mistral Medium 3.1
By Mistral AI
Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases. The model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3.1 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.
Release Date
13 Aug 2025
Context Size
131.07K
Baidu: ERNIE 4.5 21B A3B
By baidu
A sophisticated text-based Mixture-of-Experts (MoE) model featuring 21B total parameters with 3B activated per token, delivering exceptional multimodal understanding and generation through heterogeneous MoE structures and modality-isolated routing. Supporting an extensive 131K token context length, the model achieves efficient inference via multi-expert parallel collaboration and quantization, while advanced post-training techniques including SFT, DPO, and UPO ensure optimized performance across diverse applications with specialized routing and balancing losses for superior task handling.
Release Date
12 Aug 2025
Context Size
120K
Showing page 10 of 25 with 737 models total