Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

cmd: add qwen3.5 context length for launch (#14626)

Parth Sareen562c76d7cc15
diff --git a/cmd/config/integrations.go b/cmd/config/integrations.go
index acf458abe..87c81c37d 100644
--- a/cmd/config/integrations.go
+++ b/cmd/config/integrations.go
@@ -90,6 +90,7 @@ var cloudModelLimits = map[string]cloudModelLimit{
"qwen3-coder:480b": {Context: 262_144, Output: 65_536},
"qwen3-coder-next": {Context: 262_144, Output: 32_768},
"qwen3-next:80b": {Context: 262_144, Output: 32_768},
+ "qwen3.5": {Context: 262_144, Output: 32_768},
}
// recommendedVRAM maps local recommended models to their approximate VRAM requirement.