hf:Qwen/Qwen3.5-397B-A17B

Price: See Synthetic pricing page

Qwen 3.5 is a large MoE model (397B total / 17B active) self-hosted by Synthetic. It was launched in beta on February 20, 2026.

• Pros: Fast — fast enough that Synthetic didn’t need beta rate limits for it. Decent at code, decent at agentic work. Self-hosted, so more reliable than proxied models.
• Cons: Not quite at the level of GLM-5 or Kimi K2.5 for frontier coding tasks. Performance “isn’t great tbh” (per Synthetic staff) compared to the flagship models.