IsAnythingDownFree early version
INFERENCE & GPU CLOUD

DeepInfra status

Official core-service and monitored model statuses.

Is DeepInfra down right now?

The official report lists DeepInfra as operational within the reported scope. Collected 06 Oct 2026, 16:34:56 UTC (0 min ago). Incident updates are not included in this report.

DeepInfra's own core-service and monitored-model status fields. These are provider observations, not independent generation tests; incident and maintenance details are not imported here.

Official status

Provider report
Operational

DeepInfra reports operational. 2 core services and 154 monitored models included.

DeepInfra's own core-service and monitored-model status fields. These are provider observations, not independent generation tests; incident and maintenance details are not imported here.

Collected 06 Oct 2026, 16:34:56 UTCProvider last updated 06 Oct 2026, 16:34:10 UTC
ComponentReported status
APIOperational
WebsiteOperational
all-MiniLM-L12-v2Operational
all-MiniLM-L6-v2Operational
all-mpnet-base-v2Operational
Audio8-TTS-Preview-0.6bOperational
bge-base-en-v1.5Operational
bge-en-iclOperational
bge-large-en-v1.5Operational
bge-m3Operational
bge-m3-multiOperational
bge-m3-multi-8kOperational
chatterbox-multilingualOperational
chatterbox-turboOperational
clip-ViT-B-32Operational
clip-ViT-B-32-multilingual-v1Operational
csm-1bOperational
DeepSeek-R1-0528Operational
DeepSeek-V3Operational
DeepSeek-V3-0324Operational
DeepSeek-V3.1Operational
DeepSeek-V3.2Operational
DeepSeek-V4-FlashOperational
DeepSeek-V4-Flash-0731Operational
DeepSeek-V4-Flash-Vision-ExpOperational
DeepSeek-V4-ProOperational
DeepSeek-V4-Pro-0813Operational
DeepSeek-V4.1-FlashOperational
DeepSeek-V4.1-Flash-TurboOperational
e5-base-v2Operational
e5-large-v2Operational
embeddinggemma-300mOperational
FLUX-1-devOperational
FLUX-1-Redux-devOperational
FLUX-1-schnellOperational
FLUX-2-devOperational
FLUX-2-klein-4bOperational
FLUX-2-klein-9bOperational
FLUX.1-Kontext-devOperational
gemma-3-12b-itOperational
gemma-3-27b-itOperational
gemma-3-4b-itOperational
gemma-4-26B-A4B-itOperational
gemma-4-31B-itOperational
gemma-4-31B-it-turboOperational
gemma-4-E4B-itOperational
GLM-4.6Operational
GLM-4.7Operational
GLM-4.7-FlashOperational
GLM-5Operational
GLM-5.1Operational
GLM-5.2Operational
GLM-5.3Operational
GLM-5.3-FlashOperational
gpt-oss-120bOperational
gpt-oss-120b-TurboOperational
gpt-oss-20bOperational
granite-4.2-30bOperational
granite-4.2-3bOperational
granite-4.2-8bOperational
gte-baseOperational
gte-largeOperational
Hermes-3-Llama-3.1-405BOperational
Hermes-3-Llama-3.1-70BOperational
HiggsAudioV2.5Operational
Hy3Operational
Hy4-previewOperational
InklingOperational
Inkling-SmallOperational
Janus-Pro-1BOperational
Janus-Pro-7BOperational
Kimi-K2.5Operational
Kimi-K2.6Operational
Kimi-K2.7-CodeOperational
Kimi-K3Operational
Kokoro-82MOperational
L3-8B-Lunaris-v1-TurboOperational
L3.1-70B-Euryale-v2.2Operational
Ling-3.0-flashOperational
Ling-3.0-flash-FinOperational
Ling-3.0-flash-VLOperational
Llama-3.3-70B-Instruct-TurboOperational
Llama-4-Maverick-17B-128E-Instruct-FP8Operational
Llama-4-Scout-17B-16E-InstructOperational
Llama-Guard-4-12BOperational
llama-nemotron-embed-vl-1b-v2Operational
llama-nemotron-rerank-vl-1b-v2Operational
Meta-Llama-3.1-70B-Instruct-TurboOperational
Meta-Llama-3.1-8B-Instruct-TurboOperational
MiMo-V2.5Operational
MiMo-V2.5-ProOperational
MiMo-V2.6-FlashOperational
MiMo-V2.6-Flash-RLOperational
MiMo-V2.6-ProOperational
Ming-Image-0.1-DesignOperational
Ming-Image-0.1-Design-LayerOperational
MiniMax-M2.7Operational
MiniMax-M3Operational
Mistral-Nemo-Instruct-2407Operational
Mistral-Small-24B-Instruct-2501Operational
Mistral-Small-3.2-24B-Instruct-2506Operational
multi-qa-mpnet-base-dot-v1Operational
multilingual-e5-largeOperational
multilingual-e5-large-instructOperational
Muse-Glimmer-30BOperational
MythoMax-L2-13bOperational
Nemotron-3-DiarizationOperational
Nemotron-3-Diarization-previewOperational
Nemotron-3-Embed-1B-BF16Operational
Nemotron-3-Embed-1B-NVFP4Operational
Nemotron-3-Embed-8BOperational
Nemotron-3-Nano-30B-A3BOperational
Nemotron-3.5-ASR-Streaming-Multilingual-0.6bOperational
Nemotron-Content-Safety-3.5Operational
NVIDIA-Nemotron-3-Super-120B-A12BOperational
NVIDIA-Nemotron-3-Ultra-550B-A55BOperational
NVIDIA-Nemotron-3.5-LightningOperational
orpheus-3b-0.1-ftOperational
paraphrase-MiniLM-L6-v2Operational
phi-4Operational
Qwen-Image-EditOperational
Qwen2.5-72B-InstructOperational
Qwen3-14BOperational
Qwen3-235B-A22B-Instruct-2507Operational
Qwen3-30B-A3BOperational
Qwen3-32BOperational
Qwen3-ASR-0.6BOperational
Qwen3-ASR-1.7BOperational
Qwen3-Coder-480B-A35B-Instruct-TurboOperational
Qwen3-Embedding-0.6BOperational
Qwen3-Embedding-4BOperational
Qwen3-Embedding-8BOperational
Qwen3-Next-80B-A3B-InstructOperational
Qwen3-Reranker-0.6BOperational
Qwen3-Reranker-4BOperational
Qwen3-Reranker-8BOperational
Qwen3-TTSOperational
Qwen3-TTS-VoiceDesignOperational
Qwen3-VL-235B-A22B-InstructOperational
Qwen3-VL-30B-A3B-InstructOperational
Qwen3.5-122B-A10BOperational
Qwen3.5-27BOperational
Qwen3.5-35B-A3BOperational
Qwen3.5-397B-A17BOperational
Qwen3.5-9BOperational
Qwen3.6-27BOperational
Qwen3.6-35B-A3BOperational
Qwen3.8-2.4T-A95BOperational
Qwen3.8-27BOperational
sdxl-turboOperational
Step-3.7-FlashOperational
text2vec-base-chineseOperational
Voxtral-Mini-3B-2507Operational
Voxtral-Small-24B-2507Operational
whisper-large-v3Operational
whisper-large-v3-turboOperational

Status history

Each point shows the most severe saved state that day, separate from current status. Gaps stay gray; history starts with our first observation.

Regional availability is not independently verified. View coverage.

2026-09-07Oldest → newest · UTC2026-10-01
Official reportProvider-reported state · collection time
NormalDegraded / recheckingOutage / failing checkMaintenanceNo data / inconclusiveIncomplete coverageToday in progress
2026-10-01 UTC · Official reportNo saved official observations
Known status coverage
0% of the day
Missing observations
24 h 0 min
Inconclusive observations
0 min
Saved observations
0

Durations describe observed reports or saved check states, bounded by freshness limits. They are not measured uptime or exact incident durations. Select a point, or use ← / → within a row.

Regional observations

Independent checks
No probe targets configured for this service.
View coverage details →

Official incidents in the latest report

Incident updates are not included in this collected report. Open the official status page for updates.

Scheduled maintenance

Maintenance updates are not included in this collected report.

Future maintenance is displayed separately and does not change the current status.

Understanding DeepInfra status

What does the DeepInfra report cover?

Official core-service and monitored model statuses.

How should I interpret a missing or old DeepInfra report?

Check the collection time and report scope. A missing report establishes no current availability. An expired report describes the last known state. A collection failure does not establish a DeepInfra outage.

How to check an AI service failure →

Related service reports

Reports for related products and services in the same category. Each has its own scope and coverage; these links do not establish a dependency or an available alternative.

Hugging FaceConfigured official sourceReplicateConfigured official sourceTogether AIConfigured official sourceGroqConfigured official sourceFireworks AIConfigured official sourceOpenRouterNot automatically collected

Status data checked at 06 Oct 2026, 16:35:05 UTC. Refresh reads saved data; it does not request the official source.