Nodes/ComfyUI-Qwen3.5/Qwen 3.5 (WaveSpeed API)
ComfyUI Node

Qwen 3.5 (WaveSpeed API)

A ComfyUI node in Qwen3.5 with 11 inputs and 2 outputs.

By workordie·Created 5 months ago·Updated 5 months ago· 38
Qwen 3.5 (WaveSpeed API)
  • image
  • RESPONSE
  • THINKING
modelQwen3.5-27B
promptDescribe this image in detail.
system_prompt
max_tokens4096
temperature1.00
top_p0.95
top_k20
thinkingtrue
api_key
image_url
CategoryQwen3.5

Inputs (11)

NameTypeDefaultDescription
modelCOMBOQwen3.5-27BWaveSpeed model. 35B-A3B: $0.16/$1.30 per M tokens. 27B: $0.20/$1.60. 122B-A10B: $0.26/$2.10. 397B-A17B: $0.39/$2.30 (best quality).
promptSTRINGDescribe this image in detail.Text prompt for the model
system_promptSTRINGOptional system prompt
max_tokensINT409664–81920Maximum tokens to generate
temperatureFLOAT1.000–2Sampling temperature. Thinking: 1.0, instruct: 0.7
top_pFLOAT0.950–1Nucleus sampling. Thinking: 0.95, instruct: 0.8
top_kINT201–100Top-K sampling
thinkingBOOLEANtrueEnable thinking/reasoning mode (reasoning_effort: medium). Disable for faster, cheaper responses.
api_keySTRINGWaveSpeed API key. Leave empty to use WAVESPEED_API_KEY env var.
imageoptIMAGESingle image input (resized + base64 encoded)
image_urloptSTRINGImage URL — sent directly to API, no base64. Preferred over image input.

Outputs (2)

NameTypeDescription
RESPONSESTRING
THINKINGSTRING