Hanzo Models via Hanzo AI

Zen model: claude-3-5-haiku

Zen model: claude-3-7-sonnet

Zen model: claude-4-1-opus

Zen model: claude-haiku-4-5

Zen model: claude-opus-4

Zen model: claude-opus-4-5

Zen model: claude-opus-4-6

Zen model: claude-sonnet-4

Zen model: claude-sonnet-4-5

Zen model: deepseek-r1-distill-70b

Zen model: gpt-4.1

Zen model: gpt-4o

Zen model: gpt-4o-mini

Zen model: gpt-5

Zen model: gpt-5-mini

Zen model: gpt-5-nano

Zen model: gpt-5.1-codex-max

Zen model: gpt-5.2

Zen model: gpt-5.2-pro

Zen model: gpt-oss-120b

Zen model: gpt-oss-20b

Zen model: llama-3.1-8b

Zen model: llama-3.3-70b

Zen model: mistral-nemo

Zen model: o1

Zen model: o3

Zen model: o3-mini

High-quality text embeddings for RAG, search, and classification.

Content safety classifier for moderation and guardrails. 9 safety categories, 119 languages.

Ultra-lightweight model for edge deployment and low-latency tasks.

Multimodal model supporting text, vision, audio, and structured output.

Vision-language model for image understanding and visual reasoning.

Flagship MoE model for complex reasoning and multi-domain tasks.

Code-specialized MoE model for generation, review, debugging, and agentic programming.

Lightweight code model optimized for speed and inline completions.

Full-precision BF16 code model for maximum accuracy on complex codebases.

Most capable model for complex reasoning, analysis, and agentic tasks. 1M token context window.

Ultra-fast lightweight model optimized for speed and cost efficiency.

Efficient MoE model for demanding workloads with strong reasoning at production-grade cost.

Dedicated reasoning model with explicit chain-of-thought capabilities.

Maximum reasoning capability with extended chain-of-thought on MoE architecture.

Next-generation agentic frontier model with native chain-of-thought.

High-throughput agentic model for demanding production workloads.

Maximum context agentic model for document-scale analysis.

Deepest reasoning model. Multi-pass chain-of-thought with self-verification.

Efficient agentic model delivering zen5-class intelligence at a fraction of the cost.