Hanzo/ blog
Back to all articles
modelsanthropicopenaigatewaythird-party

Now Available: Claude Opus 4.6 and GPT-5.3 Codex on the Hanzo Gateway

Anthropic's Claude Opus 4.6 and OpenAI's GPT-5.3 Codex are now available through the Hanzo AI Gateway — same API, same key, zero markup.

Two major model launches this week, both live on Hanzo within 48 hours of release.

Claude Opus 4.6

Anthropic's new flagship is available now via the Hanzo AI Gateway. Claude Opus 4.6 brings multimodal capabilities with strong reasoning performance across text and vision tasks.

curl https://llm.hanzo.ai/v1/chat/completions \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -d '{"model": "anthropic/claude-opus-4.6", "messages": [{"role": "user", "content": "Hello"}]}'

GPT-5.3 Codex

OpenAI's code-specialized model is also live. GPT-5.3 Codex brings multimodal support and is purpose-built for programming workflows — generation, refactoring, debugging, and code review.

curl https://llm.hanzo.ai/v1/chat/completions \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -d '{"model": "openai/gpt-5.3-codex", "messages": [{"role": "user", "content": "Refactor this function..."}]}'

Zero Markup, Same API

Both models are available at provider pricing with zero markup. Use the same API key and endpoint you use for our Zen models or any other model on the platform. No separate accounts, no separate billing.

Over 100 models from every major provider are now available through a single Hanzo API key at hanzo.ai.

Read more

Now Available: Claude Sonnet 4.6 and Qwen3.5-397B — Multimodal MoE at Scale

Claude Sonnet 4.6 and Qwen3.5-397B-A17B are now available on the Hanzo AI Gateway — Anthropic's latest alongside the largest open-source multimodal MoE model.

Now Available: Qwen3.5-35B-A3B and Mercury 2 — Efficient MoE and Frontier Reasoning

Qwen3.5-35B-A3B (Apache 2.0, multimodal MoE) and Inception's Mercury 2 are now available on the Hanzo AI Gateway.

Now Available: Gemini 3.1 Pro — Google's 1M-Token Reasoning Model

Google's Gemini 3.1 Pro is now available on the Hanzo AI Gateway — featuring a 1M-token context window and multimodal reasoning across text, images, audio, video, and code.