==== Qwen 3.5 397B ====

''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 [[:models:glm-5|GLM-5]] or [[:models:kimi-k25|Kimi K2.5]] for frontier coding tasks. Performance "isn't great tbh" (per Synthetic staff) compared to the flagship models.

<WRAP center round info 60%>
Qwen 3.5 is still in **beta**. Performance may improve as Synthetic optimizes serving.
</WRAP>