Early warning for the AI APIs you build on
Outages, price changes, deprecations and new models — in one feed.
Next retirement: in 3 days (2026-10-20) — 5 models, e.g. Google: Gemini 2.5 Pro (batch)
Today
Fireworks: resolved — Service Degradation for Qwen 3.8 Max
We've resolved the incident and the affected service is now operational.
Show all 2 ▾
Yesterday
OpenAI: resolved — Delayed Costs data in the Compliance API
All impacted services have now fully recovered.
Thu 15 Oct
OpenAI: resolved — Widespread feature degradation
All impacted services have now fully recovered.
Fireworks: resolved — Service Degradation for Qwen 3.8 Max
We've resolved the incident and the affected service is now operational.
Fireworks: resolved — Service Degradation for Kimi K3
We've resolved the incident and the affected service is now operational.
Show all 2 ▾
Fireworks: resolved — CSP outage affecting multiple serverless models
Service has been restored for all affected serverless models. This incident is resolved.
Wed 14 Oct
Fireworks: resolved — Service Degradation for Deepseek V4.1 Flash
We've resolved the incident and the affected service is now operational.
Fireworks: resolved — Service Degradation for GLM 5.3 Fast
We've resolved the incident and the affected service is now operational.
OpenAI: resolved — Limited availability on gpt-image-2.5-flare and gpt-image-2.5-sunburst
All impacted services have now fully recovered.
OpenAI: resolved — Degraded performance in Codex and ChatGPT Work
All impacted services have now fully recovered.
Fireworks: resolved — Service Degradation for GLM 5.3
We've resolved the incident and the affected service is now operational.
Tue 13 Oct
Anthropic: resolved — Elevated errors on platform.claude.com
This issue has been resolved.
OpenAI: resolved — Degraded performance in GPT-6.1 Sol Codex and Work mode
We have resolved the issue causing degraded performance with GPT-6.1 Sol in Codex and ChatGPT Work.
Fireworks: resolved — Service Degradation for GLM 5.3
We've resolved the incident and the affected service is now operational.
Show all 2 ▾
Mon 12 Oct
Groq: resolved — Model Performance or Availability Issue
The issues affecting **minimaxai/minimax-m2.7** have been **resolved**. The model is operating normally. Root cause: **hardware connectivity issues**. We apologize for the disrupti…
Fireworks: resolved — Service Degradation for GLM 5.3
We've resolved the incident and the affected service is now operational.
OpenAI: resolved — Delayed Costs data in the Compliance API
All impacted services have now fully recovered.
Fireworks: resolved — Service Degradation for GLM 5.3
We've resolved the incident and the affected service is now operational.
Fireworks: resolved — Service Degradation for Kimi K3
We've resolved the incident and the affected service is now operational.
Fireworks: resolved — Service Degradation for GLM 5.3
We've resolved the incident and the affected service is now operational.
Groq: resolved — GroqCloud Console Errors Affecting Multiple Regions
The **Groqcloud console issue has been resolved**. All services are operating normally. We apologize for the disruption and **appreciate your patience**.
Fireworks: resolved — Service Degradation for GLM 5.3
We've resolved the incident and the affected service is now operational.
Sun 11 Oct
Fireworks: resolved — Service Degradation for GLM 5.3
We've resolved the incident and the affected service is now operational.
Sat 10 Oct
Groq: resolved — Model Performance or Availability Issue - minimaxai/minimax-m2.7
The issues affecting **minimaxai/minimax-m2.7** have been **resolved**. The model is operating normally. Root cause: **Data center hardware issues**. We apologize for the disruptio…
OpenAI: resolved — Some ChatGPT content may be unavailable on Android
All impacted services have now fully recovered.
Fri 9 Oct
OpenAI: resolved — Workspace admins may be unable to manage plugins
All impacted services have now fully recovered.
Perplexity: resolved — Elevated API errors and timeouts
The issue affecting the Website, App, and Computer has been resolved. All services are operational. The API remained operational throughout this incident.
Thu 8 Oct
OpenAI: resolved — Some APAC users are seeing errors in ChatGPT Work, conversations, and GPTs.
All impacted services have now fully recovered.
OpenAI: resolved — Elevated errors with GPT-5.6 Instant in FedRAMP workspaces
All impacted services have now fully recovered.
Wed 7 Oct
Anthropic: resolved — Issue with spend limits
We have identified an issue which resulted in some organizations to be incorrectly paused for having reached their spend limit, resulting in refused requests on the Claude API, Cla…
OpenAI: resolved — Degraded performance in Codex and Work mode: Dot turn failures, delayed responses, and reduced proactivity
All impacted services have now fully recovered.
OpenAI: resolved — Dot in Codex may fail to create new threads
All impacted services have now fully recovered.
OpenAI: resolved — Unable to create new ChatGPT Work threads in latest version of desktop app
We have released an updated app version with the fix for Linux, macOS and Windows. Affected users should update to the latest version.
OpenAI: resolved — Workspace Agents Degraded and Responses Impacted
All impacted services have now fully recovered.
Anthropic: resolved — Elevated errors loading usage data on platform.claude.com
This incident has been resolved. From 17:00 PT on October 6 / 00:00 UTC on October 7 to 18:40 PT on October 6 / 01:40 UTC on October 7, many requests to load usage data on the plat…
Tue 6 Oct
OpenAI: resolved — Computer Use Is Experiencing Issues
All impacted services have now fully recovered.
OpenAI: resolved — Errors processing large PDFs in the Responses API
All impacted services have now fully recovered.
Anthropic: resolved — Elevated errors for Claude Opus 5.5
The issue affecting Claude Opus 5.5 has been resolved.
Mon 5 Oct
Anthropic: resolved — Elevated errors for Claude Mythos 5.1 and Claude Fable 5.1
The issue affecting Claude Mythos 5.1 and Claude Fable 5.1 has been resolved. Impact occurred from 05:40 PT / 12:40 UTC to 06:10 PT / 13:10 UTC.
Thu 1 Oct
Anthropic: resolved — Delayed credits on the Claude Platform
This issue has been resolved.
Tue 29 Sept
Anthropic: resolved — Elevated errors on claude.ai, Claude Code, Claude Cowork and the Claude API
The issue affecting Claude.ai, the Claude desktop and mobile apps, Claude Code, Claude Cowork, and the Claude API has been resolved, and services have been operating normally since…
Tue 22 Sept
Anthropic: resolved — Elevated errors for multiple models
This issue has been resolved. Impact occurred from 5:50pm PT / 00:50 UTC to 7:10pm PT / 02:10 UTC.
Wed 16 Sept
Anthropic: resolved — Issues with Google Play subscriptions
This issue has been resolved.
Tue 15 Sept
Anthropic: resolved — Intermittent error spikes for Claude Mythos 5.1 and Claude Fable 5.1
A fix has been deployed for Claude Mythos 5.1 and Claude Fable 5.1 and we are monitoring to ensure it has resolved the issue.
Mon 14 Sept
Anthropic: resolved — Degraded functionality for Claude Cowork on Windows
This issue has been resolved. Microsoft has released a September 14 Windows update that fixes it: https://support.microsoft.com/en-us/servicing/os/windows-11/2026/09/kb5129195-wind…
Fri 11 Sept
Anthropic: resolved — Elevated errors for Claude Mythos 5.1 and Claude Fable 5.1
The issue affecting Claude services has been resolved. Impact occurred from 13:57 to 14:20 UTC
Thu 10 Sept
Anthropic: resolved — Elevated latency on the Claude API for some users
The issue affecting Claude services has been mitigated.
Sat 5 Sept
Perplexity: resolved — We have identified few connectors that are impacting users.
This incident has been resolved.
Thu 3 Sept
Perplexity: resolved — Issue with usage based billing
This incident has been resolved.
Anthropic: resolved — Elevated errors for multiple models
The issue affecting Claude Mythos 5.1, Claude Fable 5.1, and Claude Opus 5 has been resolved. Impact has ended as of 9:16 PT / 16:16 UTC.
Anthropic: resolved — Elevated errors for Claude Sonnet 5
This incident has been resolved.
Tue 1 Sept
Cohere: resolved — Multiple Endpoint Disruptions
🎉 The issue has been resolved and we are back to normal.
Perplexity: resolved — Computer Tasks Degraded
This incident has been resolved.
Fri 14 Aug
Perplexity: resolved — Computer Sandbox Errors
This incident has been resolved.
Thu 13 Aug
Perplexity: resolved — Investigating API issue
This incident has been resolved.
Thu 6 Aug
Perplexity: resolved — Computer Sandbox Issue
This incident has been resolved.
Wed 5 Aug
Cohere: resolved — Documentation Content Loading Issues
🎉 The issue has been resolved and we are back to normal.
Thu 23 Jul
Cohere: resolved — Dashboard Login Service Disruption
🎉 The issue affecting Dashboard login has been resolved. All Cohere services are operating normally. Thank you for your patience while we worked through this.
Perplexity: resolved — Computer sandbox issues
This incident has been resolved.
Thu 2 Jul
Perplexity: resolved — Computer Sandbox Issue
This incident has been resolved.
Groq: resolved — Data Center Failure Impacting Capacity
The **capacity issue has been resolved**. All services are operating at normal capacity. The incident was caused by a **power loss issue that led to a cooling system failure at one…
Tue 30 Jun
Perplexity: resolved — Computer Sandbox Issue
This incident has been resolved.
Fri 5 Jun
Perplexity: resolved — Connector connectivity issues
This incident has been resolved.
Mon 1 Jun
Cohere: resolved — /audio/transcriptions endpoint returns error for audio files with unexpected sampling rate
🎉 The issue has been resolved and we are back to normal.
Fri 8 May
Perplexity: resolved — Perplexity Website and API incident
This incident has been resolved.
Mon 20 Apr
Cohere: resolved — Docs Platform Degraded Performance
Docs are back up!
Mon 13 Apr
Cohere: resolved — Multiple Model Disruptions
🎉 The issue has been resolved and we are back to normal.
Sat 11 Apr
Cohere: resolved — Scheduled DB Maintenance: Model authentication and API access momentarily affected
🎉 The issue has been resolved and we are back to normal.
Thu 19 Mar
Groq: resolved — openai/gpt-oss-120b Performance Issue
The issues affecting openai/gpt-oss-120b have been **resolved**. The model is operating normally. Actions were taken to cancel billing plans and restrict verification status of org…
Mon 16 Feb
Perplexity: resolved — Sonar API incident
This incident has been resolved.
Fri 13 Feb
Cohere: resolved — Some chat models are unresponsive or timing out
The issue has been resolved and all models are back to normal operation
Sat 7 Feb
Groq: resolved — meta-llama/llama-4-scout-17b-16e-instruct Degraded Performance
This incident has been resolved. Thank you for your patience.
Thu 5 Feb
Perplexity: resolved — An issue affecting the stability of the website has been detected
This incident has been resolved.
Groq: resolved — meta-llama/llama-4-scout-17b-16e-instruct Degraded Performance
The issues affecting meta-llama/llama-4-scout-17b-16e-instruct have been **resolved**. The model is once again operating normally. We apologize for the disruption and thank you for…
Show all 2 ▾
Tue 27 Jan
Groq: resolved — meta-llama/llama-4-scout-17b-16e-instruct Degraded Performance
This incident has been resolved. Thank you for your patience.
Sat 24 Jan
Groq: resolved — Data Center Failure Impacting Model Latency - SYD
This incident is now resolved.
Thu 25 Dec
Groq: resolved — Model Performance or Availability Issue: llama-3.3-70b-versatile
The issues affecting **llama-3.3-70b-versatile** have been **resolved**. The model is operating normally. We apologize for the disruption and thank you for your patience.
Sun 14 Dec
Groq: resolved — Data Center Failure Impacting Capacity - DMM1
**The data center capacity issue has been resolved. All services are operating at normal capacity. The incident was caused by a failed ARP entry on the network gateway device cause…
Sat 6 Dec
Groq: resolved — meta-llama/llama-4-scout-17b-16e-instruct Degraded Performance
The issues affecting meta-llama/llama-4-scout-17b-16e-instruct , meta-llama/llama-4-maverick-17b-128e-instruct, & groq/compound have been **resolved**. The models are operating nor…
Fri 5 Dec
Perplexity: resolved — Service outage
This incident has been resolved.
Tue 2 Dec
Groq: resolved — meta-llama/llama-4-scout-17b-16e-instruct & groq/compound Degraded Performance
The issues affecting meta-llama/llama-4-scout-17b-16e-instruct & groq/compound have been **resolved**. Both of the models are operating normally. We apologize for the disruption an…
Tue 18 Nov
Groq: resolved — Console, Website, & API Availability Issues: Global Cloudflare Outage
We are resolving this incident as we have now observed ~30 minutes of normalized service availability and customer traffic. We will continue to closely monitor our systems for any …
Sat 18 Oct
Cohere: resolved — Chat models return 503 service error when /v1/chat requests omit message and chat_history while providing tool_results
🎉 The issue has been resolved and we are back to normal.
Wed 1 Oct
Cohere: resolved — logprobs param degeraded for `command-a-03-2025` and `command-a-reasoning-08-2025`
`logprobs` feature has been correctly marked as unavailable for the specified models.
Thu 7 Aug
Cohere: resolved — Command-a-vision-07-2025 degraded performance
🎉 The issue has been resolved and we are back to normal.
Fri 25 Jul
Cohere: resolved — Model serving infrastructure outage
🎉 The issue has been resolved and we are back to normal.
Thu 12 Jun
Cohere: resolved — GCP Outage
🎉 The issue has been resolved and we are back to normal.
Wed 21 May
Cohere: resolved — Degraded service affecting embed-v4.0
🎉 The issue has been resolved and we are back to normal.
Tue 13 May
Cohere: resolved — Degraded service affecting embedding models
🎉 The issue has been resolved and we are back to normal.