Guide

Qwen omni model for text, vision, audio, and multimodal agent tasks

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...

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...

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...

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen reasoning model for deliberate problem solving, math, and coding

Qwen reasoning model for deliberate problem solving, math, and coding

Qwen instruction model for multilingual chat, reasoning, and tool use

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...

Image model for prompt-driven generation, editing, and visual design workflows

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.

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.

Speech transcription model for accurate audio-to-text and captioning workflows

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...

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...

Kimi K2 Instruct 0905 from Groq - text input, 262,144 token context

Fast Kimi model for responsive chat, coding help, and agent loops

Kimi model for long-context chat, coding, and agentic reasoning

Kimi K2 0905 from Synthetic - text input, 262,144 token context

Kimi K2 0905 from DeepInfra - text input, 262,144 token context

Flagship Qwen model for complex reasoning, coding, and agentic workflows

Kimi model for long-context chat, coding, and agentic reasoning

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...

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.

Efficient model for low-latency assistance, extraction, and routine automation

General-purpose chat model for instruction following, writing, and analysis

Kimi model for long-context chat, coding, and agentic reasoning

Translation model for multilingual conversion, localization, and cross-language workflows

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.

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)

LucidQuery is an advanced AI platform pushing toward general intelligence through hybrid multimodal capabilities that seamlessly integrate reasoning, web search, coding, and geolocation intelligence. Key features include multimodal reasoning across text, images, audio, video, code, and structured data for deep contextual understanding, precision geolocation intelligence with spatial analysis and map-based entity search, advanced coding AI for programming problem-solving and automation, real-time web search integration for up-to-date evidence-based responses, and explainable structured outputs combining logical reasoning with generative capabilities. The platform provides API access enabling developers to build sophisticated applications requiring multi-format data processing and real-world spatial context, designed for use cases spanning financial modeling, geographic analysis, research, and complex workflow automation.

Gemini Live 2.5 Flash from Google - text, image, audio, video input, 128,000 token context

Coding model for repository understanding, refactors, and agentic engineering tasks

Qwen instruction model for multilingual chat, reasoning, and tool use

Efficient Qwen thinking model for local reasoning, math, and coding agents

Qwen instruction model for multilingual chat, reasoning, and tool use

Multimodal reasoning model for visual analysis, planning, and tool use

Multimodal reasoning model for visual analysis, planning, and tool use

Efficient Qwen thinking model for local reasoning, math, and coding agents

Qwen instruction model for multilingual chat, reasoning, and tool use

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.

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...

Grok Code Fast 1 from xAI - text input, 256,000 token context

Translation model for multilingual conversion, localization, and cross-language workflows

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...

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...

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...

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.

Nano Banana image model for fast generation, edits, and character-consistent assets

Gemini 2.5 Flash Image (Preview) from Google - text, image input, 32,768 token context