Models

Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient…

Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.

Qwen3.8 27B is an open-weight dense vision-language model from Qwen.

Qwen3.8 Flash is a multimodal reasoning model from Alibaba.

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.

Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.

Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.

Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total.

Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3).

Fugu Max is the cost-performance model in Sakana AI's Fugu family.

Fugu Ultra is the higher-performance model in Sakana AI's Fugu family.

Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family.

Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world.

*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*.

Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of…

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of…

The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request.

Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts.

Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window.

Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window.

Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows.