DeployWhere

Baseten

AI model inference, training, model APIs, and self-hosted deployments.

No reviews yet. Write the first.
Visit Baseten

Baseten is a GPU and AI hosting provider based in an undisclosed country. No European datacenter locations are recorded for it yet. A free tier is available. Its CLOUD Act exposure has not been verified. Pricing on this page is published only after a human has reviewed it.

PricingPros and consSpecificationsAboutReviews
Company based in
Not verified
European regions
None listed
US CLOUD Act
Not verified
GDPR agreement
Not verified
Free tier
New accounts receive credits for free experimentation with deployments.
VAT
Shown excluding VAT
Baseten website
Website image published by Baseten.

Pricing

28 plans
  • Basic
    Pay as you go. Includes dedicated deployments, model APIs, training, fast cold starts, SOC 2 Type II and HIPAA compliance, and email and in-app chat support.
    Monthly
    0 USD
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Pro
    Volume discounts available. Includes Basic features plus priority access to high-demand GPUs, dedicated compute, higher Model API rate limits, engineering expertise, and dedicated Slack and Zoom support.
    Monthly
    Not listed
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Enterprise
    Volume discounts available. Includes custom SLAs, self-host deployments, on-demand flex compute, existing cloud commitments, data residency controls, advanced security and compliance, custom global regions, and advanced RBAC with Teams.
    Monthly
    Not listed
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Kimi K3
    Model API price per 1M tokens: Input $3.00, Cache Input $0.30, Output $15.00.
    Monthly
    $3.00
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Kimi K2.6
    Model API price per 1M tokens: Input $0.95, Cache Input $0.16, Output $4.00.
    Monthly
    $0.95
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Kimi K2.7 Code
    Model API price per 1M tokens: Input $0.95, Cache Input $0.16, Output $4.00.
    Monthly
    $0.95
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Inkling-Small
    Model API price per 1M tokens: Input $0.50, Cache Input $0.10, Output $1.20.
    Monthly
    $0.50
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Inkling
    Model API price per 1M tokens: Input $1.00, Cache Input $0.17, Output $4.05.
    Monthly
    $1.00
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • GLM-5.2
    Model API price per 1M tokens: Input $1.40, Cache Input $0.14, Output $4.40.
    Monthly
    $1.40
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • GLM-5.2 Fast
    Model API price per 1M tokens: Input $2.10, Cache Input $0.21, Output $6.60.
    Monthly
    $2.10
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • GLM 4.7
    Model API price per 1M tokens: Input $0.60, Cache Input $0.12, Output $2.20.
    Monthly
    $0.60
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • NVIDIA Nemotron 3 Ultra
    Model API price per 1M tokens: Input $0.60, Cache Input $0.12, Output $2.40.
    Monthly
    $0.60
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • DeepSeek-V4-Flash-0731
    Model API price per 1M tokens: Input $0.13, Cache Input $0.028, Output $0.26.
    Monthly
    $0.13
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • DeepSeek V4 Pro
    Model API price per 1M tokens: Input $1.74, Cache Input $0.145, Output $3.48.
    Monthly
    $1.74
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • GPT OSS 120B
    Model API price per 1M tokens: Input $0.10, Output $0.50. Cache Input is shown as '-'.
    Monthly
    $0.10
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • T4
    Dedicated Deployments and Training. Price per minute. 16 GiB VM.
    Monthly
    $0.01052
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • L4
    Dedicated Deployments and Training. Price per minute. 24 GiB VRAM.
    Monthly
    $0.01414
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • A10G
    Dedicated Deployments and Training. Price per minute. 24 GiB VM.
    Monthly
    $0.02012
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • A100
    Dedicated Deployments and Training. Price per minute. 80 GiB VRAM.
    Monthly
    $0.06667
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • H100 MIG
    Dedicated Deployments and Training. Price per minute. 40 GiB VRAM.
    Monthly
    $0.0625
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • H100
    Dedicated Deployments and Training. Price per minute. 80 GiB VRAM.
    Monthly
    $0.10833
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • B200
    Dedicated Deployments and Training. Price per minute. 180 GiB VRAM.
    Monthly
    $0.16633
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • 1x2
    Dedicated Deployments and Training. Price per minute.
    Monthly
    $0.00058
    vCPU
    1
    Memory
    2 GB
    Storage
    Not listed
  • 1x4
    Dedicated Deployments and Training. Price per minute.
    Monthly
    $0.00086
    vCPU
    1
    Memory
    4 GB
    Storage
    Not listed
  • 2x8
    Dedicated Deployments and Training. Price per minute.
    Monthly
    $0.00173
    vCPU
    2
    Memory
    8 GB
    Storage
    Not listed
  • 4x16
    Dedicated Deployments and Training. Price per minute.
    Monthly
    $0.00346
    vCPU
    4
    Memory
    16 GB
    Storage
    Not listed
  • 8x32
    Dedicated Deployments and Training. Price per minute.
    Monthly
    $0.00691
    vCPU
    8
    Memory
    32 GB
    Storage
    Not listed
  • 16x64
    Dedicated Deployments and Training. Price per minute.
    Monthly
    $0.01382
    vCPU
    16
    Memory
    64 GB
    Storage
    Not listed

Pros and cons

What works

  • Basic has a $0 monthly charge.
  • Compute is billed only while models use compute.
  • Self-hosted and hybrid deployments are available.
  • SOC 2 Type II and HIPAA are stated.

What to watch

  • Pro and Enterprise pricing is not published.
  • Compute prices are usage based rather than fixed monthly allocations.
  • The page does not list specific datacenter countries.
  • Support level varies by plan.

Specifications

Supported runtimes
Open source models, Custom models, Fine-tuned models, Models built in any framework
Egress policy
Not stated.
Certifications
SOC 2 Type II, HIPAA
Uptime sla
99.99% out of the box
Support
Support varies by plan and includes email, in-app chat, Slack, Zoom, and dedicated engineering support.

About Baseten

Baseten provides dedicated inference deployments, pre-optimized Model APIs, model training, and self-hosted or hybrid deployment options. Basic has no monthly platform charge and uses pay as you go pricing, while Pro and Enterprise pricing is quote based. Compute is metered by the minute, and Model APIs are priced per 1M tokens.

Reviews

None yet

No approved reviews yet. Every review is read by a person before it appears, and only approved reviews count toward a rating.

Other gpu and ai hosting

See all
DataCrunch
Finland
Exoscale GPU
Switzerland
IONOS AI
Germany
Nebius
Netherlands
OVHcloud AI
France
Scaleway GPU Instances
France

Something here out of date?

Every figure on this page was checked by a person, and providers change their plans without telling anybody. Say what moved and it gets checked again.

Work at Baseten? Claim this listing to correct the description and add screenshots. Verification is a confirmation link to an address on your own domain. Pricing still goes through the same check as every other listing here.