Rankings

Model rankings

The most-used models on the Flow AI network over the last 7 days — with the live clearing price and how far below published rates they cleared. Updated every few minutes.

#ModelRequests (7d)Avg latencyPrice $/M outSavings
1minimax-m3
39,842
6257 ms$0.140087.3% off
2byo:GLM Coding Max
16,390
5901 ms
3byo:MiniMax-M3
16,010
6455 ms
4deepseek-v4-flash
15,316
3773 ms$0.26605% off
5byo:MiMo Subscription
13,706
6651 ms
6byo:MiniMax-M2.7-highspeed
12,513
8007 ms
7byo:Codex spark
11,021
5338 ms
8byo:Codex gpt-5-mini
9,312
8672 ms
9byo:MiniMax-M2.1
9,022
6476 ms
10minimax-m2.7
7,288
10590 ms$0.110088.4% off
11byo:Codex GPT
6,985
8573 ms
12byo:MiniMax-M2
6,374
5981 ms
13byo:MiniMax-M2.1-highspeed
5,853
7310 ms
14byo:MiniMax-M2.5-highspeed
5,834
7331 ms
15byo:MiniMax-M2.5
5,825
6568 ms
16mimo-v2.5
5,556
7838 ms$0.240080% off
17byo:MiniMax-M2.7
5,019
8063 ms
18byo:GLM 5.1
4,482
7623 ms
19byo:Codex gpt-5.5-codex
4,471
9232 ms
20byo:Kimi For Coding
4,396
14593 ms
21byo:Codex gpt-5.1-codex-mini
4,368
9072 ms
22byo:Codex gpt-5.5-mini
4,337
9079 ms
23byo:Codex gpt-4.1-mini
4,190
8969 ms
24byo:GLM 5.2
3,847
7461 ms
25byo:Codex codex-mini
3,831
9137 ms
26byo:Codex gpt-5-codex
3,225
9230 ms
27byo:Codex o4-mini
2,935
9537 ms
28gemini-2.5-flash
1,162
2748 ms$2.5000
29claude-sonnet-4.6
1,118
3062 ms$15.0000
30nemotron-3-ultra
853
15182 ms$0.0000
31gpt-4o-mini
468
2933 ms$0.300050% off
32mimo-v2.5-pro
308
12704 ms$2.4000
33phi-4-miniself-host
267
10688 ms$0.0800
34mistral-smallself-host
188
1597 ms$0.2400
35gpt-oss-120b
185
7589 ms$0.1900
36nvidia/nemotron-3-ultra-550b-a55b-20260604:free
185
37deepseek-v4-pro
122
27576 ms$0.8700
38byo:Codex gpt-5-nano
115
6147 ms
39byo:Codex gpt-4o-mini
58
6398 ms
40gemma3-4bself-host
44
11045 ms$0.1000

See all models & live prices or how Flow AI compares to OpenRouter.