API error Failures
See which AI models run into API error most often, so you can spot reliability risks before choosing one. Sort by: Failure Count ↑.
149/149
Filter models
No models match the current search and filters.
| Rank | Model | Company | API error Count | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #142 | Muse Wonder xhigh | Meta | 6 | 0.8 | $4.012 | 14/23 | 34.4s |
| #188 | Ember-1 low | Fireworks | 6 | 0.7 | $1.488 | 13/23 | 34.9s |
| #429 | Nemotron 3 Nano Omni 30b A3b Reasoning medium | NVIDIA | 6 | 0.3 | $0.000 | 4/19 | 17.1s |
| #431 | Nemotron 3 Nano Omni 30b A3b Reasoning default | NVIDIA | 6 | 0.3 | $0.000 | 2/19 | 728ms |
| #196 | Ember-1 high | Fireworks | 7 | 0.7 | $2.405 | 12/23 | 58.1s |
| #365 | Hy3 preview high | Tencent | 7 | 0.5 | $0.135 | 11/21 | 56.6s |
| #383 | Hy3 preview low | Tencent | 7 | 0.5 | $0.042 | 10/21 | 24.6s |
| #384 | Ring 2.6 1t default | Inclusionai | 7 | 0.4 | $0.026 | 9/23 | 48.9s |
| #214 | Ember-1 max | Fireworks | 8 | 0.7 | $3.264 | 11/23 | 97.3s |
| #398 | Qwen3.6 Plus Preview medium | Qwen | 8 | 0.4 | $0.000 | 9/19 | 15.2s |
| #417 | Command A+ medium | Cohere | 22 | 0.3 | $0.064 | 0/23 | 91.7s |
| #423 | Command A+ high | Cohere | 22 | 0.3 | $0.079 | 0/23 | 90.0s |
| #427 | Command A+ low | Cohere | 22 | 0.3 | $0.073 | 0/23 | 92.5s |
| #426 | Command A+ none | Cohere | 23 | 0.3 | $0.000 | 0/23 | 77.9s |