Baseten
InferenceProduction ML model deployment — custom + open models
Operational
All systems responding normally
Last checked 21/09/2026, 9:43:17 am
335ms response
Uptime History98.00% uptime
2026-09-19Today
Uptime
98.00%
Avg Latency
394ms
P95 Latency
554ms
Fastest
245ms
Checks
150
Response Time
Last 60 checks245ms min394ms avg607ms 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
335ms21 Sept, 09:43 am
Operational
278ms21 Sept, 09:34 am
Operational
575ms21 Sept, 09:21 am
Operational
375ms21 Sept, 09:09 am
Operational
405ms21 Sept, 08:52 am
Operational
461ms21 Sept, 08:42 am
Operational
563ms21 Sept, 08:34 am
Operational
588ms21 Sept, 08:22 am
Operational
417ms21 Sept, 08:09 am
Operational
414ms21 Sept, 07:53 am
Operational
414ms21 Sept, 07:42 am
Operational
298ms21 Sept, 07:34 am
Operational
555ms21 Sept, 07:21 am
Operational
486ms21 Sept, 07:09 am
Operational
370ms21 Sept, 06:52 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