JatevoStatus
Subscribe

DeepSeek unavailable; GPT and Kimi remain operational

Request telemetry · rolling 15-minute evaluation

Updated 8s ago

Auto-refreshes every 30s

Model availability

Current availability follows each model's latest fresh request. Rolling metrics retain earlier failures, so a recovered route can be operational while its recent aggregate still shows failures.

GPT 5.6 SOL

Jatevo's primary GPT 5.6 route.

The latest request completed successfully; 100.0% platform success over the last 15 minutes.

Operational
2 requests / 15m0 platform 5xx100.00% platform successLast observed 2m agoModel docs

GPT 5.5

Codex-compatible GPT inference route.

The latest request completed successfully; 100.0% platform success over the last 15 minutes.

Operational
3 requests / 15m0 platform 5xx100.00% platform successLast observed 43s agoModel docs

DeepSeek V4 Flash 0731

DeepSeek V4 Flash across configured execution lanes.

The latest request returned a platform failure; 49.4% platform success over the last 15 minutes.

Major outage
79 requests / 15m40 platform 5xx49.367% platform successLast observed 1m agoModel docs

Kimi

Kimi K3 and K2.7 Code across configured account lanes.

The latest request completed successfully; 97.5% platform success over the last 15 minutes.

Operational
40 requests / 15m1 platform 5xx97.50% platform successLast observed 39s agoModel docs

Systems

Platform 5xx failures determine availability. Capacity limits and client errors are measured separately.

API Gateway

OpenAI-compatible inference at api.jatevo.ai/v1.

27.1% of requests returned platform 5xx failures in the last 15 minutes.

Major outage
90 days ago86.309% platform successToday
155 requests / 15m42 platform 5xx0 capacity 42928 s p95Open service

Inference Router 02

Dedicated inference routing at 2.jatevo.ai/v1.

Request latency is elevated above the service objective.

Degraded performance
125 requests / 15m0 platform 5xx0 capacity 429124 s p95Open service

Inference Router 03

Multi-provider inference routing at 3.jatevo.ai/v1.

The service is reachable; no requests were observed in the last 15 minutes.

Operational
0 requests / 15m0 platform 5xx0 capacity 429-- p95Open service

Website and Console

Jatevo website, account console, and authentication entry points.

The service is reachable; no requests were observed in the last 15 minutes.

Operational
Independent live probe · historical request telemetry is not available for this component yet.Open service

Documentation

Model catalog, API documentation, and integration guides.

The service is reachable; no requests were observed in the last 15 minutes.

Operational
Independent live probe · historical request telemetry is not available for this component yet.Open service

Incidents

Investigating · detected Sep 1, 2026, 23:38 UTC

Major outage affecting API Gateway

27.1% of requests returned platform 5xx failures in the last 15 minutes.

Major outage

Investigating · detected Sep 2, 2026, 08:23 UTC

Degraded performance on Inference Router 02

Request latency is elevated above the service objective.

Degraded performance

Resolved Sep 2, 2026, 08:22 UTC

Degraded performance on Inference Router 02

Request latency is elevated above the service objective.

Resolved

Resolved Sep 2, 2026, 08:20 UTC

Degraded performance on Inference Router 02

Request latency is elevated above the service objective.

Resolved

Resolved Sep 2, 2026, 08:17 UTC

Degraded performance on Inference Router 02

Request latency is elevated above the service objective.

Resolved

Resolved Sep 2, 2026, 08:04 UTC

Degraded performance on Inference Router 02

Request latency is elevated above the service objective.

Resolved

Resolved Sep 2, 2026, 07:50 UTC

Degraded performance on Inference Router 02

Request latency is elevated above the service objective.

Resolved

Resolved Sep 2, 2026, 07:47 UTC

Degraded performance on Inference Router 02

Request latency is elevated above the service objective.

Resolved

Resolved Sep 2, 2026, 07:39 UTC

Degraded performance on Inference Router 02

Request latency is elevated above the service objective.

Resolved

Resolved Sep 2, 2026, 06:19 UTC

Degraded performance on Inference Router 02

Request latency is elevated above the service objective.

Resolved

Resolved Sep 2, 2026, 05:13 UTC

Degraded performance on Inference Router 02

Request latency is elevated above the service objective.

Resolved

Resolved Sep 2, 2026, 05:01 UTC

Degraded performance on Inference Router 02

Request latency is elevated above the service objective.

Resolved

How status is calculated

Aggregate request telemetry plus independent health probes. Current state uses a rolling 15-minute window. Platform failures are HTTP 5xx responses; HTTP 429 and client 4xx are reported separately.

Thresholds: degraded 1% · partial outage 5% · major outage 20%.