Qwen3.5-122B-A10B is 1.7× cheaper per million tokens (blended). Gemini 3.7 Flash has the larger context window (1,048,576 vs 262,144 tokens, 4.0×). Qwen3.5-122B-A10B is open-weights; the other is not.

Gemini 3.7 Flash vs Qwen3.5-122B-A10B

Live catalog fields. Best-in-row is highlighted.

Gemini 3.7 Flash

Google · google__gemini-3.7-flash

Qwen3.5-122B-A10Bopen

Qwen · qwen__qwen3.5-122b-a10b

Identity

Fieldgoogle__gemini-3.7-flashqwen__qwen3.5-122b-a10b
ProviderGoogleQwen
Sluggoogle__gemini-3.7-flashqwen__qwen3.5-122b-a10b
Statuslivelive
Open weightsNoYes
License
HuggingFaceQwen/Qwen3.5-122B-A10B

Quality

Fieldgoogle__gemini-3.7-flashqwen__qwen3.5-122b-a10b
Quality index (0–100)86.7

Cost

Fieldgoogle__gemini-3.7-flashqwen__qwen3.5-122b-a10b
Input $ / 1M tokens$0.75$0.29
Cached input $ / 1M$0.07
Output $ / 1M tokens$3.75$2.40

Context

Fieldgoogle__gemini-3.7-flashqwen__qwen3.5-122b-a10b
Max context tokens1,048,576262,144
Max output tokens65,53681,920

Modalities

Fieldgoogle__gemini-3.7-flashqwen__qwen3.5-122b-a10b
Inputtext, image, video, file, audiotext, image, video
Outputtexttext