
Please rotate your device
To continue exploring this website, please rotate your device to a vertical orientation
Modelmammoth-1
Input$0.10
Cache input—
Output—
Modelelephant-1
Input$0.035
Cache input—
Output—
Modeljoey-1
Input$0.01
Cache input—
Output—
ModelBeam
Input$0.40
Cache input$0.04
Output$1.20
ModelMuse Spark Open
Input$1.25
Cache input$0.15
Output$4.25
ModelGLM-5.3 Fast
Input$2.10
Cache input$0.21
Output$6.60
ModelGLM-5.3
Input$1.40
Cache input$0.14
Output$4.40
ModelGLM-5.3-Flash
Input$0.15
Cache input$0.03
Output$0.50
ModelGLM-5.2 Fast
Input$2.10
Cache input$0.21
Output$6.60
ModelGLM-5.2
Input$1.40
Cache input$0.14
Output$4.40
ModelDeepSeek V4.1 Flash 1017 Fast
Input$0.60
Cache input$0.014
Output$2.40
ModelDeepSeek V4.1 Flash 1017
Input$0.30
Cache input$0.007
Output$1.20
ModelDeepSeek V4.1 Flash Fast
Input$0.60
Cache input$0.014
Output$2.40
ModelDeepSeek V4.1 Flash
Input$0.30
Cache input$0.007
Output$1.20
ModelDeepSeek V4 Pro 0813
Input$1.32
Cache input$0.132
Output$3.96
ModelDeepSeek-V4-Flash-0731
Input$0.13
Cache input$0.028
Output$0.26
ModelKimi K3.1 Pro
Input$2.00
Cache input$0.20
Output$10.00
ModelKimi K3
Input$3.00
Cache input$0.30
Output$15.00
ModelNemotron 3.5 Super VL
Input$0.20
Cache input$0.04
Output$0.50
ModelNVIDIA Nemotron 3 Ultra
Input$0.60
Cache input$0.12
Output$2.40
ModelGPT OSS 120B
Input$0.10
Cache input—
Output$0.50
GPUT4
Memory16 GiB VM
Per Minute$0.01052
Approx / hour$0.6312
GPUL4
Memory24 GiB VRAM
Per Minute$0.01414
Approx / hour$0.8484
GPUA10G
Memory24 GiB VM
Per Minute$0.02012
Approx / hour$1.2072
GPUA100
Memory80 GiB VRAM
Per Minute$0.06667
Approx / hour$4.00
GPUH100 MIG
Memory40 GiB VRAM
Per Minute$0.0625
Approx / hour$3.75
GPUH100
Memory80 GiB VRAM
Per Minute$0.10833
Approx / hour$6.50
GPUB200
Memory180 GiB VRAM
Per Minute$0.16633
Approx / hour$9.98
GPU1x2
Memory1 vCPU, 2 GiB RAM
Per Minute$0.00058
Approx / hour$0.0348
GPU1x4
Memory1 vCPU, 4 GiB RAM
Per Minute$0.00086
Approx / hour$0.0516
GPU2x8
Memory2 vCPUs, 8 GiB RAM
Per Minute$0.00173
Approx / hour$0.1038
GPU4x16
Memory4 vCPUs, 16 GiB RAM
Per Minute$0.00346
Approx / hour$0.2076
GPU8x32
Memory8 vCPUs, 32 GiB RAM
Per Minute$0.00691
Approx / hour$0.4146
GPU16x64
Memory16 vCPUs, 64 GiB RAM
Per Minute$0.01382
Approx / hour$0.8292
GPUT4
Memory16 GiB VM
Per Minute$0.01052
Approx / hour$0.6312
GPUL4
Memory24 GiB VRAM
Per Minute$0.01414
Approx / hour$0.8484
GPUA10G
Memory24 GiB VM
Per Minute$0.02012
Approx / hour$1.2072
GPUA100
Memory80 GiB VRAM
Per Minute$0.06667
Approx / hour$4.00
GPUH100 MIG
Memory40 GiB VRAM
Per Minute$0.0625
Approx / hour$3.75
GPUH100
Memory80 GiB VRAM
Per Minute$0.10833
Approx / hour$6.50
GPUB200
Memory180 GiB VRAM
Per Minute$0.16633
Approx / hour$9.98
ModelGLM-5.320% off for limited time
Prefill$3.02
Prefill Cached$0.60
Sample$9.72
Train$11.66
ModelGLM-5.3-Flash20% off for limited time
Prefill$0.67
Prefill Cached$0.13
Sample$1.69
Train$4.46
ModelQwen3.6 35B-A3B20% off for limited time
Prefill$0.36
Prefill Cached$0.07
Sample$1.07
Train$1.71
ComputeCPU
Rate$0.0655 vCPU / hr
ComputeMemory
Rate$0.0211 GiB RAM / hr
StorageSnapshots
Rate$0.20 GiB / month
StorageVolumes
Rate$0.16 GiB / month
ImagesImages stored
Rate$0.045 GiB / month
ImagesBuilds
Ratesame price as a sandbox
Secure capacity
and pricing
Work with Baseten on custom pricing, volume discounts, priority compute, custom regions, SLAs, and support.