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.
| # | Model | Requests (7d) | Avg latency | Price $/M out | Savings |
|---|---|---|---|---|---|
| 1 | minimax-m3 | 39,842 | 6257 ms | $0.1400 | 87.3% off |
| 2 | byo:GLM Coding Max | 16,390 | 5901 ms | — | — |
| 3 | byo:MiniMax-M3 | 16,010 | 6455 ms | — | — |
| 4 | deepseek-v4-flash | 15,316 | 3773 ms | $0.2660 | 5% off |
| 5 | byo:MiMo Subscription | 13,706 | 6651 ms | — | — |
| 6 | byo:MiniMax-M2.7-highspeed | 12,513 | 8007 ms | — | — |
| 7 | byo:Codex spark | 11,021 | 5338 ms | — | — |
| 8 | byo:Codex gpt-5-mini | 9,312 | 8672 ms | — | — |
| 9 | byo:MiniMax-M2.1 | 9,022 | 6476 ms | — | — |
| 10 | minimax-m2.7 | 7,288 | 10590 ms | $0.1100 | 88.4% off |
| 11 | byo:Codex GPT | 6,985 | 8573 ms | — | — |
| 12 | byo:MiniMax-M2 | 6,374 | 5981 ms | — | — |
| 13 | byo:MiniMax-M2.1-highspeed | 5,853 | 7310 ms | — | — |
| 14 | byo:MiniMax-M2.5-highspeed | 5,834 | 7331 ms | — | — |
| 15 | byo:MiniMax-M2.5 | 5,825 | 6568 ms | — | — |
| 16 | mimo-v2.5 | 5,556 | 7838 ms | $0.2400 | 80% off |
| 17 | byo:MiniMax-M2.7 | 5,019 | 8063 ms | — | — |
| 18 | byo:GLM 5.1 | 4,482 | 7623 ms | — | — |
| 19 | byo:Codex gpt-5.5-codex | 4,471 | 9232 ms | — | — |
| 20 | byo:Kimi For Coding | 4,396 | 14593 ms | — | — |
| 21 | byo:Codex gpt-5.1-codex-mini | 4,368 | 9072 ms | — | — |
| 22 | byo:Codex gpt-5.5-mini | 4,337 | 9079 ms | — | — |
| 23 | byo:Codex gpt-4.1-mini | 4,190 | 8969 ms | — | — |
| 24 | byo:GLM 5.2 | 3,847 | 7461 ms | — | — |
| 25 | byo:Codex codex-mini | 3,831 | 9137 ms | — | — |
| 26 | byo:Codex gpt-5-codex | 3,225 | 9230 ms | — | — |
| 27 | byo:Codex o4-mini | 2,935 | 9537 ms | — | — |
| 28 | gemini-2.5-flash | 1,162 | 2748 ms | $2.5000 | — |
| 29 | claude-sonnet-4.6 | 1,118 | 3062 ms | $15.0000 | — |
| 30 | nemotron-3-ultra | 853 | 15182 ms | $0.0000 | — |
| 31 | gpt-4o-mini | 468 | 2933 ms | $0.3000 | 50% off |
| 32 | mimo-v2.5-pro | 308 | 12704 ms | $2.4000 | — |
| 33 | phi-4-miniself-host | 267 | 10688 ms | $0.0800 | — |
| 34 | mistral-smallself-host | 188 | 1597 ms | $0.2400 | — |
| 35 | gpt-oss-120b | 185 | 7589 ms | $0.1900 | — |
| 36 | nvidia/nemotron-3-ultra-550b-a55b-20260604:free | 185 | — | — | — |
| 37 | deepseek-v4-pro | 122 | 27576 ms | $0.8700 | — |
| 38 | byo:Codex gpt-5-nano | 115 | 6147 ms | — | — |
| 39 | byo:Codex gpt-4o-mini | 58 | 6398 ms | — | — |
| 40 | gemma3-4bself-host | 44 | 11045 ms | $0.1000 | — |
See all models & live prices or how Flow AI compares to OpenRouter.