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 |
|---|---|---|---|---|
| Mistral AI | 0 | 0 | — | 100 |
| Meta AI | 0 | 0 | — | 100 |
| Perplexity | 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 |
| Azure OpenAI | 0 | 0 | — | 100 |
| Replicate | 1 | 60 | 60 min | 96 |
Citations
- Increased Authentication Failures Affecting Some Users (cite)
- Elevated errors on Claude Opus 4.6 (cite) official
- Elevated errors on claude.ai (cite) official
- 【已恢复】DeepSeek 网页/APP 性能异常（[Resolved]DeepSeek Web/APP Service Degraded Performance） (cite) official
- Sonnet 4.6 elevated error rate (cite) official
- GPT 5.2 Elevated Error Rates (cite)
- Claude Desktop login issues (cite) official
- Elevated errors on claude.ai (cite) official
- Vertex AI Gemini API customers experienced increased error rates when accessing the global endpoint. (cite) official
- Outage in usage reporting (cite) official
- Elevated errors on claude.ai (cite) official
- Claude Code showing "JSON Parse error: Unexpected EOF" and writing excessive files on Windows (cite) official
- Gen3 Alpha Turbo generations are taking longer than normal (cite) official
- Issue with some ChatGPT Apps (cite)
- Claude Desktop failing to open for some users (cite) official
- Artifact generation (asking the model to generate a spreadsheet or slideshow) on ChatGPT is down for all users. (cite)
- We've identified a problem and are working on a fix (cite) official
- We've identified a problem and are working on a fix (cite) official
- Claude for Government not loading (cite) official
- Elevated errors on Claude Opus 4.6 (cite) official