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.
Two significant releases from the past week are live on the Hanzo AI Gateway.
Claude Sonnet 4.6
Anthropic shipped Claude Sonnet 4.6 on February 17 — the workhorse model for teams that need strong reasoning at a lower price point than Opus. It delivers excellent performance across coding, analysis, and creative tasks.
Now available through the standard gateway endpoint:
curl https://llm.hanzo.ai/v1/chat/completions \
-H "Authorization: Bearer $HANZO_API_KEY" \
-d '{"model": "anthropic/claude-sonnet-4.6", "messages": [{"role": "user", "content": "..."}]}'
Qwen3.5-397B-A17B — Open Source Multimodal MoE
Released February 16 by the Alibaba Qwen team, Qwen3.5-397B-A17B is a 397B-parameter Mixture of Experts model with only 17B active parameters per forward pass. It's natively multimodal, handling text and image inputs, and delivers strong benchmark performance while being remarkably efficient to run.
Key specs:
- 397B total / 17B active — MoE architecture
- Multimodal — text + vision input
- Open source — permissive license
- Strong reasoning — competitive with proprietary models at the frontier
curl https://llm.hanzo.ai/v1/chat/completions \
-H "Authorization: Bearer $HANZO_API_KEY" \
-d '{"model": "qwen/qwen3.5-397b-a17b", "messages": [{"role": "user", "content": "..."}]}'
The Gateway Advantage
Every new model release — open or proprietary — is available through the same Hanzo API key you already use. No new accounts, no new SDKs, no new billing relationships. Just change the model name in your request.
100+ models from every major provider, all at hanzo.ai.
Read more
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: GLM-5 (744B) and MiniMax M2.5 (230B) — Two Open-Source Giants
GLM-5 and MiniMax M2.5 — two of the largest open-source models ever released — are now available through the Hanzo AI Gateway.
Now Available: Google Gemma 3n and Gemma 3 270M — On-Device AI Goes Multimodal
Google's Gemma 3n (multimodal on-device) and Gemma 3 270M (smallest Gemma ever) are now available on the Hanzo AI Gateway.