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 81.5 / 100

Gemini 3.7 Flash

Google · Closed flagship

Elo: 1,530 (Top 23%)TTFT: 82 ms (Top 1%)Speed: 215 tok/s (Top 1%)Out $: $1.875/1M (Top 50%)

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

Elo1,466TTFT88 msSpeed188 tok/sOut $$0.6/1M

Rank #2 in stackvs #1

#3DeepSeek V4 Flash(DeepSeek)

Score 73.3

Elo1,490TTFT165 msSpeed142 tok/sOut $$0.28/1M

Rank #3 in stackvs #1

#4Yi-Lightning(01.AI)

Score 72.6

Elo1,475TTFT150 msSpeed130 tok/sOut $$0.14/1M

Rank #4 in stackvs #1

#5Doubao Lite 1.5(ByteDance)

Score 67.3

Elo1,360TTFT110 msSpeed180 tok/sOut $$0.1/1M

Rank #5 in stackvs #1

#6Llama 4 Scout(Meta)

Score 66.0

Elo1,412TTFT130 msSpeed155 tok/sOut $$0.3/1M

Rank #6 in stackvs #1

#7Llama 4 Maverick(Meta)

Score 64.7

Elo1,468TTFT170 msSpeed130 tok/sOut $$0.8/1M

Rank #7 in stackvs #1

#8Gemini 2.0 Flash Thinking(Google)

Score 63.3

Elo1,490TTFT220 msSpeed115 tok/sOut $$0.4/1M

Rank #8 in stackvs #1

#9Doubao Pro 1.5(ByteDance)

Score 61.9

Elo1,470TTFT190 msSpeed105 tok/sOut $$0.28/1M

Rank #9 in stackvs #1

#10GLM-5.3(Zhipu)

Score 58.1

Elo1,558TTFT255 msSpeed90 tok/sOut $$1.8/1M

Rank #10 in stackvs #1