Model Rankings
AI Model Leaderboard
Ranked by real request volume over the past 7 days through ModelAPI · Updated hourly · with pricing & performance scores
17+
Models tracked
8.2T
Tokens this week
DS V4 Flash +344%
Hottest model
$0.13/M
Lowest price
#ModelWk TokensInput /MOutput /MContextQualityWeekly Δ
1
Claude Opus 4.8
Anthropic
LiveFlagship
—
$4.75
$23.75
1M
98
+48%
2
Kimi K2.7 Code
Moonshot
LatestCode
—
$0.95
$4.00
256K
90
+22%
3
Claude Opus 4.7
Anthropic
ReasoningCode
935B
$4.75
$23.75
200K
97
+19%
4
DeepSeek V4 Flash🔥 Hot
DeepSeek
CheapestFast
704B
$0.14
$0.28
1M
85
+344%
5
GPT-5.5
OpenAI
FrontierReasoning
450B
$2.50
$10.00
256K
96
+41%
6
Gemini 3.1 Pro
Google
1M ctxMultimodal
296B
$2.00
$12.00
1.048576M
93
-20%
7
Claude Sonnet 4.6
Anthropic
CodeBalanced
1.35T
$2.85
$14.25
1M
94
+1%
8
DeepSeek V4 Pro
DeepSeek
ValueReasoning
907B
$0.50
$1.00
1M
91
+29%
9
Kimi K2.6
Moonshot
Long ctxChinese
182B
$0.55
$2.65
256K
88
+15%
10
Grok 4.1 Fast
xAI
FastReasoning
646B
$1.25
$2.50
1M
89
+13%
11
GPT-5.4
OpenAI
BalancedOpenAI
310B
$2.50
$10.00
128K
92
-5%
12
Llama 4 Maverick
Meta
Open SourceFast
198B
—
—
—
87
+8%
13
Qwen Max
Alibaba
ChineseValue
156B
$0.40
$1.20
33K
86
+22%
14
Minimax M2.7
Minimax
ChineseLong ctx
729B
$0.30
$1.20
205K
85
+8%
15
GPT-5.4 Mini
OpenAI
FastCheap
280B
$0.15
$0.60
128K
83
+3%
16
GLM-5
Zhipu AI
LatestChinese
90B
$1.00
$4.00
200K
82
+45%
17
Gemini 3.1 Flash
Google
FastCheap
973B
$0.50
$3.00
1.048576M
82
+6%
Quality score: weighted across public benchmarks · Speed score: based on P50 response latency
Browse full model catalog