MCP sequential-thinkinghttps://github.com/modelcontextprotocol/servers/tree/main/src/sequentialthinkingStep-wise reasoning MCP. DeepSeek-R1https://deepseek.comOpen reasoning model. GPT-6 Astrahttps://platform.openai.comOpenAI's GPT-6 frontier flagship — agentic coding, computer use, million-token retrieval. GPT-6.1 Solhttps://platform.openai.comNear-Astra capability at one-fifth the list price — the cost-efficient frontier pick. GPT-5.6 Solhttps://platform.openai.comGPT-5.6 reasoning variant. Claude Opus 5.5https://www.anthropic.com/claudeAnthropic's 5.5 flagship — SOTA Terminal-Bench 4.0 (vendor-run 66.4% xhigh; independent 59.6%). Claude Sonnet 5.5https://www.anthropic.com/claudeNear-Opus quality at Sonnet price — 30%+ faster than Sonnet 5. Claude Fable 5.1https://www.anthropic.com/claudeAnthropic Fable frontier. Claude Opus 5https://www.anthropic.com/claudeAnthropic Opus tier. DeepSeek-V4 Prohttps://deepseek.comDeepSeek V4 reasoning flagship. Muse Spark 1.3https://ai.meta.comMeta's frontier — reported 75.4% DeepSWE v1.1 at max reasoning. Nemotron Ultrahttps://build.nvidia.comNVIDIA's open reasoning model. K2 Thinkinghttps://kimi.moonshot.cnKimi K2 reasoning variant. Gemini 4 Carbonhttps://openrouter.ai/google/gemini-4-carbonGemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. Claude Fable 5.2https://openrouter.ai/anthropic/claude-fable-5.2Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. Muse Emberhttps://openrouter.ai/meta/muse-emberMuse Ember is the smallest and most efficient model from Meta that’s designed for complex reasoning execution and the work agents repeat all day: tool calls, coding agent subtasks, routing,... Gemini Omni 1.2 Flashhttps://openrouter.ai/google/gemini-omni-1.2-flashGemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash. Gemini Omni 1.1 Flashhttps://openrouter.ai/google/gemini-omni-1.1-flashGemini Omni 1.1 Flash is Google's native multimodal video generation and editing model, the generally available successor to Gemini Omni Flash Preview. GLM 5.3 FlashX Legalhttps://openrouter.ai/z-ai/glm-5.3-flashx-legalGLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. GPT-6.1 Terra Prohttps://openrouter.ai/openai/gpt-6.1-terra-proGPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. GPT-6.1 Terrahttps://openrouter.ai/openai/gpt-6.1-terraGPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. Kimi K3.1 Prohttps://openrouter.ai/moonshotai/kimi-k3.1-proKimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. MiniMax M3.1 Flashhttps://openrouter.ai/minimax/minimax-m3.1-flashMiniMax-M3.1-Flash is a multimodal model from MiniMax. Muse Spark Openhttps://openrouter.ai/meta/muse-spark-openMuse Spark Open is a coding-optimized open-weight model. Nemotron 3.5 Super VLhttps://openrouter.ai/nvidia/nemotron-3.5-super-vlNVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. Gemini 4 Argonhttps://openrouter.ai/google/gemini-4-argonGemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Muse Wonderhttps://openrouter.ai/meta/muse-wonderMuse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. Claude Haiku 5.5https://openrouter.ai/anthropic/claude-haiku-5.5Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. Nano Banana 2.1https://openrouter.ai/google/gemini-nano-banana-2.1Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. Mistral Large 4https://openrouter.ai/mistralai/mistral-large-4-0Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. GPT-6.1 Sol Prohttps://openrouter.ai/openai/gpt-6.1-sol-proGPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. GLM 5.3 Primehttps://openrouter.ai/z-ai/glm-5.3-primeGLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. Qwen3.8 Max Primehttps://openrouter.ai/qwen/qwen3.8-max-primeQwen3.8 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. Command A+https://openrouter.ai/cohere/command-a-plusCommand A+ is Cohere's flagship model for enterprise agentic workflows. GPT-6 Luna Prohttps://openrouter.ai/openai/gpt-6-luna-proGPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. GPT-6 Lunahttps://openrouter.ai/openai/gpt-6-lunaGPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. GPT-6 Sol Prohttps://openrouter.ai/openai/gpt-6-sol-proGPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. GPT-6 Solhttps://openrouter.ai/openai/gpt-6-solGPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. Grok 4.7https://openrouter.ai/x-ai/grok-4.7Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. Qwen3.8 Omni Flashhttps://openrouter.ai/qwen/qwen3.8-omni-flashQwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. GLM 5.3 FlashXhttps://openrouter.ai/z-ai/glm-5.3-flashxGLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. DeepSeek V4.1 Flashhttps://openrouter.ai/deepseek/deepseek-v4.1-flashDeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. GPT-6 Astra Prohttps://openrouter.ai/openai/gpt-6-astra-proGPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Qwen3.8 Flashhttps://openrouter.ai/qwen/qwen3.8-flashQwen3.8 Flash is a multimodal reasoning model from Alibaba. DeepSeek V4 Flash Vision Exphttps://openrouter.ai/deepseek/deepseek-v4-flash-vision-expDeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding whil Qwen3.8 27Bhttps://openrouter.ai/qwen/qwen3.8-27bQwen3.8 27B is an open-weight dense vision-language model from Qwen. Qwen3.8 2.4T A95Bhttps://openrouter.ai/qwen/qwen3.8-2.4t-a95bQwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion tot Nemotron 3.5 Lightninghttps://openrouter.ai/nvidia/nemotron-3.5-lightningNVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. Muse Glimmer 30Bhttps://openrouter.ai/meta/muse-glimmer-30bMuse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. Muse Spark 1.2https://openrouter.ai/meta/muse-spark-1.2Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. Qwen3.7 Flashhttps://openrouter.ai/qwen/qwen3.7-flashQwen3.7 Flash is a vision-language reasoning model from Alibaba. Gemini 3.5 Flash Litehttps://openrouter.ai/google/gemini-3.5-flash-liteGemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. Muse Spark 1.1https://openrouter.ai/meta/muse-spark-1.1Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. GPT-5.6 Luna Prohttps://openrouter.ai/openai/gpt-5.6-luna-proGPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. GPT-5.6 Lunahttps://openrouter.ai/openai/gpt-5.6-lunaGPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. GPT-5.6 Terra Prohttps://openrouter.ai/openai/gpt-5.6-terra-proGPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. GPT-5.6 Terrahttps://openrouter.ai/openai/gpt-5.6-terraGPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. GPT-5.6 Sol Prohttps://openrouter.ai/openai/gpt-5.6-sol-proGPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Grok 4.5https://openrouter.ai/x-ai/grok-4.5Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. GLM 5.2https://openrouter.ai/z-ai/glm-5.2GLM 5.2 is a large-scale reasoning model from Z.ai. Kimi K2.7 Codehttps://openrouter.ai/moonshotai/kimi-k2.7-codeMoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. Qwen3.7 Plushttps://openrouter.ai/qwen/qwen3.7-plusQwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. MiniMax M3https://openrouter.ai/minimax/minimax-m3MiniMax-M3 is a multimodal foundation model from MiniMax. Grok Build 0.1https://openrouter.ai/x-ai/grok-build-0.1Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. Gemini 3.5 Flashhttps://openrouter.ai/google/gemini-3.5-flashGemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. thinking-out-loud skillhttps://github.com/Shubhamsaboo/awesome-llm-apps/tree/main/agent_skills/thinking-out-loudSkill: visible agent reasoning trace.