Please rotate your device

To continue exploring this website, please rotate your device to a vertical orientation

Pricing that scales with you. From your first token to your trillionth.

Pay for what you use, or work with us to secure capacity and pricing for production workloads.

Pay as you go

Start building today

No contracts or capacity planning. Use Model APIs, Dedicated Inference, Training, and Sandboxes with transparent usage-based pricing.

  • Usage-based pricing

  • Scale up or down anytime

  • Access across the Baseten platform

Production scale

Secure capacity for production

Running at scale? Work with us on capacity, custom pricing, regions, and support for your workloads.

  • Volume discounts

  • Reserved and priority compute

  • Capacity planning and custom terms

Model APIs

Token pricing ($ per 1M tokens)

Pay for input, cached input, and output tokens.

ModelInputCache inputOutput
mammoth-1
$0.10
—
—
elephant-1
$0.035
—
—
joey-1
$0.01
—
—
Beam
$0.40
$0.04
$1.20
Muse Spark Open
$1.25
$0.15
$4.25
GLM-5.3 Fast
$2.10
$0.21
$6.60
GLM-5.3
$1.40
$0.14
$4.40
GLM-5.3-Flash
$0.15
$0.03
$0.50
GLM-5.2 Fast
$2.10
$0.21
$6.60
GLM-5.2
$1.40
$0.14
$4.40
DeepSeek V4.1 Flash 1017 Fast
$0.60
$0.014
$2.40
DeepSeek V4.1 Flash 1017
$0.30
$0.007
$1.20
DeepSeek V4.1 Flash Fast
$0.60
$0.014
$2.40
DeepSeek V4.1 Flash
$0.30
$0.007
$1.20
DeepSeek V4 Pro 0813
$1.32
$0.132
$3.96
DeepSeek-V4-Flash-0731
$0.13
$0.028
$0.26
Kimi K3.1 Pro
$2.00
$0.20
$10.00
Kimi K3
$3.00
$0.30
$15.00
Nemotron 3.5 Super VL
$0.20
$0.04
$0.50
NVIDIA Nemotron 3 Ultra
$0.60
$0.12
$2.40
GPT OSS 120B
$0.10
—
$0.50
Dedicated Inference

Compute pricing

Dedicated GPU pricing with usage-based billing.

GPUMemoryPer MinuteApprox / hour
T4
16 GiB VM
$0.01052
$0.6312
L4
24 GiB VRAM
$0.01414
$0.8484
A10G
24 GiB VM
$0.02012
$1.2072
A100
80 GiB VRAM
$0.06667
$4.00
H100 MIG
40 GiB VRAM
$0.0625
$3.75
H100
80 GiB VRAM
$0.10833
$6.50
B200
180 GiB VRAM
$0.16633
$9.98
1x2
1 vCPU, 2 GiB RAM
$0.00058
$0.0348
1x4
1 vCPU, 4 GiB RAM
$0.00086
$0.0516
2x8
2 vCPUs, 8 GiB RAM
$0.00173
$0.1038
4x16
4 vCPUs, 16 GiB RAM
$0.00346
$0.2076
8x32
8 vCPUs, 32 GiB RAM
$0.00691
$0.4146
16x64
16 vCPUs, 64 GiB RAM
$0.01382
$0.8292
Training

Training Compute

On-demand GPU pricing for fine-tuning and training.

GPUMemoryPer MinuteApprox / hour
T4
16 GiB VM
$0.01052
$0.6312
L4
24 GiB VRAM
$0.01414
$0.8484
A10G
24 GiB VM
$0.02012
$1.2072
A100
80 GiB VRAM
$0.06667
$4.00
H100 MIG
40 GiB VRAM
$0.0625
$3.75
H100
80 GiB VRAM
$0.10833
$6.50
B200
180 GiB VRAM
$0.16633
$9.98
Training

Serverless Loops token pricing ($ per 1M tokens)

Pay for prefill (uncached and cached), sample, and train tokens.

ModelPrefillPrefill CachedSampleTrain
GLM-5.320% off for limited time
$3.02
$0.60
$9.72
$11.66
GLM-5.3-Flash20% off for limited time
$0.67
$0.13
$1.69
$4.46
Qwen3.6 35B-A3B20% off for limited time
$0.36
$0.07
$1.07
$1.71
Sandboxes

Runtime Pricing

Usage-based CPU, memory, and runtime pricing for isolated agent environments.

ComputeRate
CPU
$0.0655 vCPU / hr
Memory
$0.0211 GiB RAM / hr
StorageRate
Snapshots
$0.20 GiB / month
Volumes
$0.16 GiB / month
ImagesRate
Images stored
$0.045 GiB / month
Builds
same price as a sandbox

Secure capacity and pricing

Work with Baseten on custom pricing, volume discounts, priority compute, custom regions, SLAs, and support.