Baseten
InferenceProduction ML model deployment — custom + open models
Operational
All systems responding normally
Last checked 10/06/2026, 1:46:52 pm
587ms response
Uptime History97.33% uptime
2026-06-04Today
Uptime
97.33%
Avg Latency
570ms
P95 Latency
703ms
Fastest
294ms
Checks
150
Response Time
Last 60 checks294ms min570ms avg4441ms max
💰 Pricing
custom
A10G: $0.31/hr. A100: $2.87/hr. Dedicated deployment.
⚡ Rate Limits
free
RPM: 10TPM: 1,000
Free plan: 10 RPM, 1K TPM. Paid: up to 1000 RPM.
🤖 Models (1)
| Model | Task | Context | Vision | Tools | JSON |
|---|---|---|---|---|---|
| Custom Deployment Deploy any model. A10G/A100 GPUs. | llm | — | — | — | — |
Recent Checks
Showing last 15Operational
587ms10 June, 01:46 pm
Operational
714ms10 June, 12:22 pm
Operational
424ms10 June, 11:20 am
Operational
703ms10 June, 10:04 am
Operational
611ms10 June, 09:31 am
Operational
652ms10 June, 08:52 am
Operational
427ms10 June, 08:13 am
Operational
654ms10 June, 07:36 am
Operational
641ms10 June, 06:51 am
Operational
411ms10 June, 06:05 am
Operational
492ms10 June, 05:17 am
Operational
4441ms10 June, 04:22 am
Operational
514ms10 June, 03:32 am
Operational
559ms10 June, 02:42 am
Operational
432ms10 June, 01:42 am
Other Inference Providers
Groq
LPU inference — fastest tokens per second on the market
Cerebras
Wafer-scale chip inference — 1,000+ tokens/sec
Together AI
Open-source model inference — Llama, Mixtral, FLUX
Fireworks AI
Fast open-model inference — FireFunction, Llama, Mixtral
OpenRouter
Unified API across 200+ models — route by price or speed
Hugging Face
Serverless inference API — 100k+ open models on demand