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
1qwen3-embedding-4b
202,543
3301 ms
2byo:MiniMax-M3
122,448
4786 ms
3byo:Grok 4.6
63,719
8612 ms
4byo:MiniMax-M2.7
33,484
6957 ms
5byo:MiniMax-M2.1
31,167
4574 ms
6byo:MiniMax-M2.5-highspeed
24,996
6977 ms
7byo:Claude Sonnet 5 (H)
22,886
7498 ms
8byo:MiniMax-M2
19,416
4438 ms
9byo:MiniMax-M2.5
17,951
4391 ms
10byo:GLM Coding Max
17,254
14950 ms
11byo:MiniMax-M2.1-highspeed
16,430
6622 ms
12byo:MiniMax-M2.7-highspeed
16,412
6828 ms
13byo:Kimi For Coding
12,426
10105 ms
14byo:MiMo Subscription
5,544
9394 ms
15byo:Codex spark
4,943
8465 ms
16byo:Codex GPT
4,638
8830 ms
17byo:Codex gpt-5-mini
4,109
10226 ms
18byo:GLM 5.2
3,496
6185 ms
19byo:Claude Opus 5 (H)
3,223
10846 ms
20byo:GLM 5.1
2,961
6572 ms
21or:cohere/north-mini-code:free
2,213
9976 ms$0.0000
22byo:Codex gpt-5-codex
2,188
8354 ms
23deepseek-v4-flash
2,080
3831 ms$0.2800
24byo:Codex gpt-5.5-codex
2,045
8237 ms
25byo:Codex gpt-5.1-codex-mini
1,840
8489 ms
26byo:Codex o4-mini
1,539
8835 ms
27byo:Codex gpt-4.1-mini
1,513
8511 ms
28byo:Codex gpt-5.5-mini
1,500
8995 ms
29gpt-oss-120bself-host
1,305
38403 ms$0.060056.5% off
30byo:Claude Opus 5
1,255
6531 ms
31mimo-v2.5
1,220
11466 ms$0.250078.7% off
32byo:Codex codex-mini
1,178
8515 ms
33minimax-m2.7
537
7930 ms$0.100090% off
34minimax-m3
460
8077 ms$0.130088.7% off
35byo:Claude Sonnet 5
418
6018 ms
36byo:DeepSeek V4 Pro (Ali)
407
12041 ms
37byo:Qwen 3.8 Max
242
16849 ms
38gemini-2.5-flash
165
8077 ms$2.5000
39byo:Codex gpt-4o-mini
53
11555 ms
40byo:Codex gpt-5-nano
31
6858 ms

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