Monthly Provider Scorecards
Provider reliability rollups (incident frequency, degraded minutes, MTTR).
Top providers (30d)
Reliability score = 100 - (incidents × 4) - (degraded minutes ÷ 120).
| Provider | Incidents (30d) | Degraded min | MTTR | Reliability |
|---|---|---|---|---|
| Gemini (Google) | 0 | 0 | — | 100 |
| Mistral AI | 0 | 0 | — | 100 |
| Meta AI | 0 | 0 | — | 100 |
| Perplexity | 0 | 0 | — | 100 |
| Groq | 0 | 0 | — | 100 |
| AI21 Labs | 0 | 0 | — | 100 |
| Stability AI | 0 | 0 | — | 100 |
| Hugging Face | 0 | 0 | — | 100 |
| Grok (xAI) | 0 | 0 | — | 100 |
| Amazon Bedrock (AWS) | 0 | 0 | — | 100 |
Citations
- We're seeing long setup times and high contention for models on some L40S and H200 clusters. (cite)
- Partial Service Disruption (cite) official
- We've identified a problem with generations and are working on a fix (cite) official
- Elevated error rates on Codex, ChatGPT and Responses API (cite)
- Issues with Seedance and Seedream generations (cite) official
- Elevated errors on Opus 4.7 (cite) official
- Issue affecting some Claude Code services (cite) official
- Elevated errors for ChatGPT Pro (cite)
- codex-gpt-image-2-does-not-exist-errors (cite)
- Elevated errors on multiple models (cite) official
- Guest users are experiencing elevated error rate when using ChatGPT conversations. (cite)
- We've identified an issue with Veo 3.1 generations and are working on fixing it (cite) official
- Degraded performance for Claude Sonnet 4.6 (cite) official
- Decreased ChatGPT availability for Free users (cite)
- /audio/transcriptions endpoint returns error for audio files with unexpected sampling rate (cite)
- Elevated errors on Claude Sonnet 4.6 (cite) official
- Elevated errors for Claude Opus 4.7 (cite) official
- Sonnet 4.5 elevated errors (cite) official
- Opus 4.7 elevated errors (cite) official
- opus 4.7 elevated errors (cite) official