Model Garden

Nemotron 3 Nano 30B A3B is a compact MoE model optimized for reasoning, coding, and long-context RAG workflows.

DeepSeek Chat V3.1, a powerful MoE language model with 164K context window. Excels at general chat, coding, and complex reasoning tasks with function calling support.

DeepSeek V3.2, an advanced MoE language model with 164K context window. Features improved reasoning, function calling, and general intelligence capabilities.

DeepSeek V4-Flash is a 284B total / 13B active parameter chat model with long-context support and fast, cost-efficient inference.

DeepSeek V4-Pro is a 1.6T total / 49B active parameter model with 1M context and top-tier agentic reasoning and coding capabilities.

MiniMax M2, a versatile model with 197K context window. Optimized for coding tasks with function calling and reasoning support.

MiniMax M2.5, a capable model with 197K context window. Supports function calling and reasoning for general purpose tasks.

MiniMax-M3 is a frontier multimodal coding model with a 1M context window, agentic reasoning, and tool use.

Page-to-Markdown document parser for images and PDFs.

Jev classification model: typed yes/no, choice and score questions over text or JSON state. 64k context; state plus longest question limited to 32k tokens.

Claude Fable 5.1

Qwen 3.8 27B is a multimodal reasoning model with tool use, structured outputs, and long-context support.

A multimodal document parsing model that extracts text, tables, lists, forms, images, captions, and layout into Markdown.

Gemini 3.8 Flash is our most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows—all with the speed and cost efficiency of Flash.

Speech-to-text model for transcribing supported WAV recordings with optional language bias.

GPT-6 Astra is OpenAI's flagship reasoning model for complex professional and agentic work.

Qwen3.8 Flash-Next is an ultra-efficient multimodal model with elite coding from 6B active parameters.

Claude Sonnet 4 is a significant upgrade to Claude Sonnet 3.7, delivering superior coding and reasoning while responding more precisely to your instructions.

Meta's multimodal reasoning model for coding and long-running agentic workflows, with a one-million-token context window, tool calling, and structured outputs.

Fast image generation and editing from text and image inputs.

Image generation and editing from text and image inputs, with a focus on editing precision.

GLM-5.3-Flash is Z.ai's native multimodal GLM-5 model for efficient coding, agentic workflows, visual understanding, and professional document tasks.

Jamba 1.5 Mini

Qwen-MT Flash

Qwen-MT Lite

Qwen Plus

Qwen3 Coder 30B-A3B Instruct by Alibaba, a coding-optimized MoE model with 262K context window. Specialized for code generation and function calling tasks.

Qwen3 Embedding 8B by Alibaba, an embedding model hosted on TensorX with 32K context window.

Qwen3-VL 235B-A22B

Qwen3.5 122B-A10B by Alibaba, a multimodal vision-language MoE model with 122B total and 10B active parameters across 256 experts. Supports text, image and video inputs with a 256K context window for native multimodal agent applications.