API error Failures
See which AI models run into API error most often, so you can spot reliability risks before choosing one. Sort by: Response Time (avg) ↓.
Categories
68/68
Filter models
No models match the current search and filters.
| Rank | Model | Company | API error Count | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #115 | Mimo V2 PRO medium | Xiaomi | 1 | 6.3 | $0.333 | 12/21 | 22.2s |
| #212 | gpt-oss-120b none | OpenAI | 3 | 3.7 | $0.010 | 6/19 | 21.6s |
| #119 | MiMo-V2-Flash medium | Xiaomi | 1 | 6.3 | $0.043 | 12/21 | 20.1s |
| #66 | KAT-Coder-Pro V2.5 low | Kwaipilot | 1 | 7.4 | $0.387 | 11/22 | 19.5s |
| #179 | DeepSeek V3.2 none | DeepSeek | 4 | 5.0 | $0.054 | 6/22 | 18.3s |
| #213 | Nemotron 3 Nano Omni 30b A3b Reasoning medium | NVIDIA | 6 | 3.4 | $0.000 | 4/19 | 17.1s |
| #106 | Hy3 preview medium | Tencent | 3 | 6.5 | $0.018 | 14/21 | 16.3s |
| #36 | Inkling medium | Thinkingmachines | 1 | 8.0 | $0.391 | 15/22 | 16.2s |
| #150 | KAT-Coder-Air V2.5 high | Kwaipilot | 3 | 5.6 | $0.077 | 7/22 | 15.9s |
| #181 | Qwen3.6 Plus Preview medium | Qwen | 8 | 4.9 | $0.000 | 9/19 | 15.2s |
| #192 | Laguna M.1 medium | Poolside | 4 | 4.7 | $0.033 | 9/19 | 14.7s |
| #205 | Hy3 preview none | Tencent | 4 | 4.0 | $0.003 | 4/21 | 12.9s |
| #188 | KAT-Coder-Air V2.5 none | Kwaipilot | 1 | 4.8 | $0.067 | 5/22 | 12.2s |
| #152 | Owl Alpha medium | Openrouter | 1 | 5.6 | $0.000 | 8/21 | 11.9s |
| #173 | Mistral Small 4 medium | Mistral | 2 | 5.1 | $0.096 | 5/22 | 10.8s |