Model status
Every model we can currently serve is checked with a real minimal request. The table below is the result of that probe — not a hand-maintained board. Anything that fails shows as degraded rather than being quietly hidden.
Waiting on first probe
The health probe has not returned a reading yet.
We do not publish an uptime SLA. Rather than an invented uptime percentage, each model row below shows the current probe result and, where available, its measured round-trip latency.
| Model | Model ID | Status | Latency | Uptime | Last checked |
|---|---|---|---|---|---|
| GPT-5.6 Sol | openai/gpt-5.6-sol | Not probed | — | not probed | — |
| GPT-5.6 Terra | openai/gpt-5.6-terra | Not probed | — | not probed | — |
| GPT-5.6 Luna | openai/gpt-5.6-luna | Not probed | — | not probed | — |
| GPT-5.5 | openai/gpt-5.5 | Not probed | — | not probed | — |
| GPT-5.5 Pro | openai/gpt-5.5-pro | Not probed | — | not probed | — |
| GPT-5.4 | openai/gpt-5.4 | Not probed | — | not probed | — |
| GPT-5.4 Mini | openai/gpt-5.4-mini | Not probed | — | not probed | — |
| GPT-5.4 Nano | openai/gpt-5.4-nano | Not probed | — | not probed | — |
| GPT-5.4 Pro | openai/gpt-5.4-pro | Not probed | — | not probed | — |
| GPT-5.2 | openai/gpt-5.2 | Not probed | — | not probed | — |
| GPT-5 | openai/gpt-5 | Not probed | — | not probed | — |
| GPT-5 Mini | openai/gpt-5-mini | Not probed | — | not probed | — |
| GPT-5 Nano | openai/gpt-5-nano | Not probed | — | not probed | — |
| Gemini 3.1 Pro | google/gemini-3.1-pro-preview | Not probed | — | not probed | — |
| Gemini 3.6 Flash | google/gemini-3.6-flash | Not probed | — | not probed | — |
| Gemini 3.5 Flash | google/gemini-3.5-flash | Not probed | — | not probed | — |
| Gemini 3 Flash | google/gemini-3-flash-preview | Not probed | — | not probed | — |
| Gemini 3.1 Flash Lite | google/gemini-3.1-flash-lite | Not probed | — | not probed | — |
| Gemini 2.5 Pro | google/gemini-2.5-pro | Not probed | — | not probed | — |
| Gemini 2.5 Flash | google/gemini-2.5-flash | Not probed | — | not probed | — |
| Gemini 2.5 Flash Lite | google/gemini-2.5-flash-lite | Not probed | — | not probed | — |
| GPT-OSS 120B | groq/openai/gpt-oss-120b | Not probed | — | not probed | — |
| GPT-OSS 20B | groq/openai/gpt-oss-20b | Not probed | — | not probed | — |
| Qwen 3.6 27B | groq/qwen/qwen3.6-27b | Not probed | — | not probed | — |
| Groq Compound | groq/groq/compound | Not probed | — | not probed | — |
| Groq Compound Mini | groq/groq/compound-mini | Not probed | — | not probed | — |
| Mistral Large | mistral/mistral-large-latest | Not probed | — | not probed | — |
| Mistral Medium | mistral/mistral-medium-latest | Not probed | — | not probed | — |
| Mistral Small | mistral/mistral-small-latest | Not probed | — | not probed | — |
| Magistral Small | mistral/magistral-small-latest | Not probed | — | not probed | — |
| Codestral | mistral/codestral-latest | Not probed | — | not probed | — |
| Devstral Medium | mistral/devstral-medium-latest | Not probed | — | not probed | — |
| Ministral 8B | mistral/ministral-8b-latest | Not probed | — | not probed | — |
| Ministral 3B | mistral/ministral-3b-latest | Not probed | — | not probed | — |
| Nano Banana Pro | google/gemini-3-pro-image | Not probed | — | not probed | — |
| Nano Banana 2 | google/gemini-3.1-flash-image | Not probed | — | not probed | — |
| Nano Banana | google/gemini-2.5-flash-image | Not probed | — | not probed | — |
| GPT Image 2 | openai/gpt-image-2 | Not probed | — | not probed | — |
| GPT Image 1 Mini | openai/gpt-image-1-mini | Not probed | — | not probed | — |
| Nova Voice | openai/gpt-4o-mini-tts | Not probed | — | not probed | — |
| Gemini Voice Flash | google/gemini-2.5-flash-tts | Not probed | — | not probed | — |
| Gemini Voice Pro | google/gemini-2.5-pro-tts | Not probed | — | not probed | — |
| Gemini Voice Lite | google/gemini-2.5-flash-lite-preview-tts | Not probed | — | not probed | — |
| Gemini Voice 3.1 | google/gemini-3.1-flash-tts-preview | Not probed | — | not probed | — |
| Nova Transcribe | openai/gpt-4o-transcribe | Not probed | — | not probed | — |
| Nova Transcribe Mini | openai/gpt-4o-mini-transcribe | Not probed | — | not probed | — |
| Veo 3.1 Lite | google/veo-3.1-lite | Not probed | — | not probed | — |
| Veo 3.1 Fast | google/veo-3.1-fast | Not probed | — | not probed | — |
| Veo 3.1 | google/veo-3.1 | Not probed | — | not probed | — |
Listed, not yet servable
These providers are fully integrated, but their accounts are awaiting funding from the NovaServe team. They are not probed and any request for them is refused with a clear error — never rerouted to a different model.
- Claude Opus 4.5anthropic/claude-opus-4-5Awaiting funding
- Claude Sonnet 4.5anthropic/claude-sonnet-4-5Awaiting funding
- Claude Haiku 4.5anthropic/claude-haiku-4-5Awaiting funding
- Grok 4.1xai/grok-4.1Awaiting funding
- Grok 4.1 Fastxai/grok-4.1-fastAwaiting funding
- Grok Code Fastxai/grok-code-fast-1Awaiting funding
- DeepSeek V3.2 Chatdeepseek/deepseek-chatAwaiting funding
- DeepSeek Reasonerdeepseek/deepseek-reasonerAwaiting funding
Incident history
No incidents in the last 30 days.
How these numbers are produced
- Each model receives a small live request through the same path your API calls take.
- Latency is the measured round trip of that probe, not a published figure.
- Results are cached briefly, so a reading can be up to a few minutes old.
- We do not publish an uptime percentage or an SLA; what you see here is the current probe.