A cloaked reasoning model on OpenRouter, out for community feedback. Built for coding, sustained agent work and production loads: long-horizon software engineering, complex reasoning, and multimodal workflows mixing text with images and video. Reasoning is always on at low, high or max effort, over a 1M token context with up to 131K output tokens.

OpenRouter Fusion, Quality preset, June 2026 snapshot. One prompt goes in parallel to Claude Opus 4.8, GPT-5.5 and Gemini 3 Pro with web search on, then Claude Opus 4.8 judges their answers into one, weighing agreement, contradictions and blind spots. A request costs every panel member plus the judge. The panel drifts over time.

OpenRouter Fusion, Budget preset, June 2026 snapshot. The same deliberation on cheaper members: Gemini 3 Flash, DeepSeek V3.2 and Kimi K2.7 Code answer in parallel with web search on, then Gemini 3 Flash judges them into one response. A request still costs every panel member plus the judge, far less than the Quality panel.

A stealth foundation model for agent workloads, with native tool use and long context. Strong on code generation, automated workflows and complex instruction execution, and compatible with Claude Code, OpenClaw and similar tools. Prompts and completions may be logged by the provider.

Elephant Alpha is a 100B-parameter text model focused on intelligence efficiency, delivering strong reasoning performance while minimizing token usage. It supports a 256K context window with up to 32K output tokens, function calling, structured output, and prompt caching.

A stealth model on OpenRouter with roughly 1 trillion parameters and 1M tokens of context, built for agent work: long-horizon planning, multi-step execution, and the instruction-following precision frameworks like OpenClaw need. Prompts and completions are logged by the provider and may be used for training.

A stealth omni-modal model on OpenRouter that takes visual and audio input natively, reasons across both, and acts on the result through multi-step tasks. Prompts and completions are logged by the provider and may be used for training.

Aurora Alpha is a cloaked reasoning model provided by OpenRouter to gather community feedback. Designed for speed, it is built for coding assistants, real-time conversational applications, and agentic workflows. Default reasoning effort is set to medium for fast responses; for agentic coding use cases, high effort is recommended.

A stealth model released through OpenRouter to collect community feedback, strong on coding, agent workflows, reasoning and roleplay. 200K context, with tool calling, structured outputs and step-by-step reasoning.

Z.ai's 358B open-weight model under MIT, aimed at coding and agent loops. Runs on the first-party Z.ai API, on OpenRouter, and on Cerebras for high-speed inference.

TNG's November 2025 rebuild of its R1T Chimera merge, a DeepSeek R1 derivative. It runs only on OpenRouter's free tier, with no separate weights repository published.

Prime Intellect's 106B mixture-of-experts model, 12B active per token, post-trained from GLM-4.5-Air-Base with supervised fine-tuning and reinforcement learning. Open weights under MIT.

A cloaked OpenRouter endpoint from late November 2025, later revealed as an early build of Mistral Large 3. Free while it ran, prompts logged by the provider, now retired.

A cloaked OpenRouter endpoint from November 2025, later revealed as an early snapshot of xAI's Grok 4.1 Fast with reasoning switched off. Free while it ran, prompts logged by the provider.

The thinking half of OpenRouter's Sherlock alpha pair, later revealed as an early snapshot of xAI's Grok 4.1 Fast with reasoning switched on. Free while it ran, prompts logged by the provider.

A powerful, general-purpose model that excels across real-world tasks, with standout performance in coding, tool calling, and instruction following.

Smaller reasoning model trained for image and visual understanding. Cloaked trial; prompts and outputs logged for provider feedback.

A cloaked model OpenRouter ran for community feedback: fast, general purpose, with a 2 million token context window. Takes image input and calls tools in parallel.

A cloaked model OpenRouter ran in September 2025 with a two million token context. It was later revealed as the reasoning variant of xAI's Grok 4 Fast, and the alpha endpoint has since been retired.

This is a cloaked model provided to the community to gather feedback. This is an improved version of Horizon Alpha. Note: It's free to use during this testing period, and prompts and completions are logged by the model creator for feedback and training.

This is a cloaked model provided to the community to gather feedback. Note: It's free to use during this testing period, and prompts and completions are logged by the model creator for feedback and training.

A cloaked model OpenRouter offered free in July 2025 to gather feedback, with a one million token context. The lab behind it was never publicly confirmed, prompts were logged, and the endpoint is now retired.

A stealth, powerful, all-purpose model supporting long-context tasks, including code generation. Based on community feedback.

This is a cloaked model provided to the community to gather feedback. It's a powerful, all-purpose model supporting long-context tasks, including code generation. All prompts and completions for this model are logged by the provider as well as OpenRouter.

Open-source zero-shot text-to-speech with natural prosody. Generates highly natural speech from just a reference audio clip.

Versatile open-source generative audio model capable of speech, music, and sound effects. Supports laughter, crying, and non-verbal sounds.

A cloaked reasoning model on OpenRouter, out for community feedback. Built for coding, sustained agent work and production loads: long-horizon software engineering, complex reasoning, and multimodal workflows mixing text with images and video. Reasoning is always on at low, high or max effort, over a 1M token context with up to 131K output tokens.

OpenRouter Fusion, Quality preset, June 2026 snapshot. One prompt goes in parallel to Claude Opus 4.8, GPT-5.5 and Gemini 3 Pro with web search on, then Claude Opus 4.8 judges their answers into one, weighing agreement, contradictions and blind spots. A request costs every panel member plus the judge. The panel drifts over time.

OpenRouter Fusion, Budget preset, June 2026 snapshot. The same deliberation on cheaper members: Gemini 3 Flash, DeepSeek V3.2 and Kimi K2.7 Code answer in parallel with web search on, then Gemini 3 Flash judges them into one response. A request still costs every panel member plus the judge, far less than the Quality panel.

A stealth foundation model for agent workloads, with native tool use and long context. Strong on code generation, automated workflows and complex instruction execution, and compatible with Claude Code, OpenClaw and similar tools. Prompts and completions may be logged by the provider.

Elephant Alpha is a 100B-parameter text model focused on intelligence efficiency, delivering strong reasoning performance while minimizing token usage. It supports a 256K context window with up to 32K output tokens, function calling, structured output, and prompt caching.

A stealth model on OpenRouter with roughly 1 trillion parameters and 1M tokens of context, built for agent work: long-horizon planning, multi-step execution, and the instruction-following precision frameworks like OpenClaw need. Prompts and completions are logged by the provider and may be used for training.

A stealth omni-modal model on OpenRouter that takes visual and audio input natively, reasons across both, and acts on the result through multi-step tasks. Prompts and completions are logged by the provider and may be used for training.

Aurora Alpha is a cloaked reasoning model provided by OpenRouter to gather community feedback. Designed for speed, it is built for coding assistants, real-time conversational applications, and agentic workflows. Default reasoning effort is set to medium for fast responses; for agentic coding use cases, high effort is recommended.

A stealth model released through OpenRouter to collect community feedback, strong on coding, agent workflows, reasoning and roleplay. 200K context, with tool calling, structured outputs and step-by-step reasoning.

Z.ai's 358B open-weight model under MIT, aimed at coding and agent loops. Runs on the first-party Z.ai API, on OpenRouter, and on Cerebras for high-speed inference.

TNG's November 2025 rebuild of its R1T Chimera merge, a DeepSeek R1 derivative. It runs only on OpenRouter's free tier, with no separate weights repository published.

Prime Intellect's 106B mixture-of-experts model, 12B active per token, post-trained from GLM-4.5-Air-Base with supervised fine-tuning and reinforcement learning. Open weights under MIT.

A cloaked OpenRouter endpoint from late November 2025, later revealed as an early build of Mistral Large 3. Free while it ran, prompts logged by the provider, now retired.

A cloaked OpenRouter endpoint from November 2025, later revealed as an early snapshot of xAI's Grok 4.1 Fast with reasoning switched off. Free while it ran, prompts logged by the provider.

The thinking half of OpenRouter's Sherlock alpha pair, later revealed as an early snapshot of xAI's Grok 4.1 Fast with reasoning switched on. Free while it ran, prompts logged by the provider.

A powerful, general-purpose model that excels across real-world tasks, with standout performance in coding, tool calling, and instruction following.

Smaller reasoning model trained for image and visual understanding. Cloaked trial; prompts and outputs logged for provider feedback.

A cloaked model OpenRouter ran for community feedback: fast, general purpose, with a 2 million token context window. Takes image input and calls tools in parallel.

A cloaked model OpenRouter ran in September 2025 with a two million token context. It was later revealed as the reasoning variant of xAI's Grok 4 Fast, and the alpha endpoint has since been retired.

This is a cloaked model provided to the community to gather feedback. This is an improved version of Horizon Alpha. Note: It's free to use during this testing period, and prompts and completions are logged by the model creator for feedback and training.

This is a cloaked model provided to the community to gather feedback. Note: It's free to use during this testing period, and prompts and completions are logged by the model creator for feedback and training.

A cloaked model OpenRouter offered free in July 2025 to gather feedback, with a one million token context. The lab behind it was never publicly confirmed, prompts were logged, and the endpoint is now retired.

A stealth, powerful, all-purpose model supporting long-context tasks, including code generation. Based on community feedback.

This is a cloaked model provided to the community to gather feedback. It's a powerful, all-purpose model supporting long-context tasks, including code generation. All prompts and completions for this model are logged by the provider as well as OpenRouter.

Open-source zero-shot text-to-speech with natural prosody. Generates highly natural speech from just a reference audio clip.

Versatile open-source generative audio model capable of speech, music, and sound effects. Supports laughter, crying, and non-verbal sounds.