Deterministic Stack Engine

Best AI Stack for cheapest hosted API

Output price first among models we still consider usable for chat.

Objective Weight Distribution

Elo:35%TTFT:25%Speed:20%Out $:20%

Recommended PickScore 80.9 / 100

Gemini 3.7 Flash

Google · Closed flagship

elo p76ttft ms p99tokens per sec p99output price per m p49

Output: $1.875/1MSWE-bench: 72.4%

View full model fact sheet

Full Stack Leaderboard

Ranked alternatives optimized for cheapest hosted API based on objective benchmark weighting.

#2GPT-5.6 Luna(OpenAI)

Score 75.3

eloP49ttft msP98tokens per secP95output price per mP73

Rank #2 in stackvs #1

#3DeepSeek V4 Flash(DeepSeek)

Score 72.9

eloP61ttft msP75tokens per secP81output price per mP83

Rank #3 in stackvs #1

#4Yi-Lightning(01.AI)

Score 72.3

eloP55ttft msP80tokens per secP76output price per mP89

Rank #4 in stackvs #1

#5Doubao Lite 1.5(ByteDance)

Score 67.3

eloP22ttft msP91tokens per secP92output price per mP92

Rank #5 in stackvs #1

#6Llama 4 Scout(Meta)

Score 66.3

eloP32ttft msP86tokens per secP86output price per mP82

Rank #6 in stackvs #1

#7Llama 4 Maverick(Meta)

Score 64.5

eloP51ttft msP73tokens per secP76output price per mP66

Rank #7 in stackvs #1

#8Gemini 2.0 Flash Thinking(Google)

Score 62.7

eloP61ttft msP51tokens per secP66output price per mP77

Rank #8 in stackvs #1

#9Doubao Pro 1.5(ByteDance)

Score 62.4

eloP52ttft msP63tokens per secP59output price per mP83

Rank #9 in stackvs #1

#10GLM-5.3(Zhipu)

Score 58.6

eloP86ttft msP38tokens per secP45output price per mP50

Rank #10 in stackvs #1