Kimi K2.5 is Moonshot AI's native multimodal model built on Kimi K2 with ~15T mixed visual and text tokens, delivering strong general reasoning, visual coding, and agentic tool-calling. Running inside a TEE (Trusted Execution Environment), with verifiably no logging by the provider.

Kimi K2.5 with extended thinking capabilities. Moonshot AI's native multimodal model with strong general reasoning, visual coding, and agentic tool-calling. Running inside a TEE (Trusted Execution Environment), with verifiably no logging by the provider.

GLM-4.7 is a next-gen GLM series text model with stronger reasoning, long-context chat, and reliable tool use. Running inside a TEE (Trusted Execution Environment), with verifiably no logging by the provider.

Official API route for Kimi K2.5. Uses the original Moonshot AI model version and routes directly to the Moonshot API.

Official API route for Kimi K2.5 Thinking. Uses the original Moonshot AI model version and routes directly to the Moonshot API.

Kimi K2.5 is Moonshot AI's native multimodal model built on Kimi K2 with ~15T mixed visual and text tokens, delivering strong general reasoning, visual coding, and agentic tool-calling. This route uses instant (non-thinking) mode for faster responses.

Kimi K2.5 with thinking mode enabled. Built on Kimi K2 with ~15T mixed visual and text tokens, it excels at general reasoning, visual coding, and agentic tool-calling. Produces reasoning traces for complex multi-step workflows.

Qwen3 Max is Alibaba's flagship Qwen 3 reasoning model with native tool use (web search, web extractor, code interpreter) and a 256K context window.

Allen Institute's open-source Olmo 3.1 32B Think, tuned for deep reasoning and multi-step problem solving with a 65k context window.

Allen Institute's open-source Olmo 3.1 32B Instruct, optimized for responsive instruction following and multi-turn dialogue with a 65k context window.

Dialogue-focused MiniMax model optimized for role-playing and multi-turn conversations with rich role settings.

CrucibleLab's Loki v2.0 is a Llama 3.3 70B roleplay/storytelling finetune tuned for immersive, expressive prose with strong character consistency and long-form narrative flow.

GLM-4.7-Flash is a lightweight 30B model optimized for coding and agentic tasks. Balances high performance with efficiency, perfect for local deployment. Routed directly via Z-AI (Zhipu) subscription.

GLM-4.7-Flash with extended thinking capabilities for complex reasoning. Lightweight 30B model optimized for coding and agentic tasks.

GLM-4.7-Flash is a lightweight 30B model optimized for coding and agentic tasks. Balances high performance with efficiency.

GLM-4.7-Flash with extended thinking capabilities for complex reasoning. Lightweight 30B model optimized for coding and agentic tasks.

Coding-focused GPT-5.2 variant with optimized routing.

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, better roleplaying, reasoning, multi-turn conversation, and long context coherence. This 70B model is a competitive finetune of Llama-3.1-70B focused on aligning LLMs to the user with powerful steering capabilities.

MiroThinker is the official implementation of the MiroMind Research Agent Project. It is an open-source search agent designed to advance tool-augmented reasoning and information-seeking capabilities, enabling complex real-world research workflows across diverse challenges.

Cydonia 24B v4.3 continues TheDrummer's Cydonia series with updated tuning on Mistral Small.

Magidonia 24B v4.3 is a new 24B Drummer finetune built for rich, creative roleplay.

Derestricted GLM 4.6 tuned for open-ended creative writing and roleplay with relaxed filters.

GLM-4.7 is a next-gen GLM series text model with stronger reasoning, long-context chat, and reliable tool use. Routed directly via Z-AI (Zhipu).

GLM-4.7 original with extended thinking capabilities for complex reasoning.

GLM-4.7 is a next-gen GLM series text model with stronger reasoning, long-context chat, and reliable tool use.

GLM-4.7 with extended thinking capabilities for enhanced reasoning on complex tasks.

Lightweight tier optimized for speed and cost.

The flagship model for balanced reasoning and context-rich dialogue. Perfect for AI roleplay, storytelling, and assistant tasks with a 16K window.

Tailored for deep reasoning, long-form generation, and RAG workloads. 32K token context window.

MiniMax M2.1 builds on M2 with enhanced context understanding and improved complex tool use. 230B parameter MoE model (10B active) optimized for agentic workflows and long-horizon tasks.