Zum Inhalt springen
AI.info

AI Tools

Baseten

Baseten: Preise, Fähigkeiten, Updates und Alternativen, von den Seiten des Anbieters gelesen.

Die Website von Baseten

Auf Englisch

Key facts

Price
Paid plans: see pricing Read on baseten.co
Free plan
Yes Read on baseten.co
Platforms
Web · CLI · API
API
Yes Read on baseten.co
Open source
Not presented as open source
Certifications
SOC 2 Type II · ISO 27001 · GDPR · HIPAA Read on trust.baseten.co
Last update
29 Oct 2026 Read on baseten.co
Prices checked
5 Nov 2026 Read on baseten.co

Baseten is a platform for teams building AI products. It offers dedicated inference for custom models, hosted Model APIs, managed training, agent sandboxes, and Grid for routing model requests and governing access.

Teams can deploy models from the library or their own weights, scale compute with demand, and connect trained models to production endpoints. Pricing is usage-based: Basic is listed at $0 per month, pay as you go; compute and model API usage are billed separately. Pro and Enterprise offer volume discounts or quotes, and self-hosting is listed under Enterprise.

Category
Developer Tools
Read from the maker’s pages
2026-11-18

Company

Baseten

Features

  • Deploy custom, fine-tuned, and open models as API endpoints
  • Scale inference deployments with demand and pay for compute used
  • Access hosted models through Model APIs
  • Train models with managed Training Jobs or the Loops SDK
  • Run agent commands and work with files in isolated sandboxes
  • Route model requests and manage access and usage with Baseten Grid
  • Use the Baseten CLI, dashboard, or Management API to manage sandboxes

Use cases

  • Deploy a fine-tuned model behind a production API
  • Scale inference for changing request volumes
  • Train and deploy a model using managed GPU infrastructure
  • Give an AI agent an isolated environment to run code and work with files
  • Route internal AI coding requests across approved models
  • Offer hosted model access through a branded API

Pricing

Paid plans: see pricing

Prices checked
2026-11-05
Read
by web search

Pay as you go

$0.035 per 1M input tokens (elephant-1)

  • $0.035 per 1M input tokens (elephant-1)
  • $0.10 per 1M input tokens (mammoth-1)
  • $0.01052 per minute (T4)
  • $0.0655 CPU/hr (Sandboxes compute)
  • $0.0211 GB RAM/hr (Sandboxes memory)
  • $0.20 GB per month (Sandboxes snapshots)
  • Model APIs token pricing (input, cached input, output)
  • Dedicated Inference compute per minute
  • Training compute per minute
  • Sandboxes runtime pricing
  • $0 per month, pay as you go
  • Fast cold starts, SOC 2 Type II and HIPAA compliant

Production scale

price on request

  • Volume discounts
  • Reserved/priority compute
  • Everything in Pay as you go plus custom terms

Capabilities

  • Choice of models — “You can deploy open source and custom models on Baseten.” source
  • Self-hosted — “We offer single-tenant and self-hosted deployments for extra security.” source
  • API — “Model APIs” source
  • Runs models for you — “Serve open-source, custom, and fine-tuned AI models on infra purpose-built for high-performance inference at massive scale.” source

Latest updates

Where it works

Web · CLI · API

Security

  • SOC 2 Type II — “Baseten Labs, Inc. SOC 2 Type 2 Report 5.31.26.pdf” source
  • SOC 2 — “Baseten Labs, Inc. SOC 2 Type 2 Report 5.31.26.pdf” source
  • ISO 27001 — “Baseten Labs, Inc. ISO 27001 Certificate.pdf” source
  • GDPR — “SOC 2 ISO 27001:2022 HIPAA CCPA GDPR PCI DSS - SAQ D” source
  • HIPAA — “Baseten Labs, Inc. HIPAA Report 5.31.26.pdf” source

Alternatives to Baseten

  • Together AI

    Together AI provides APIs and infrastructure for running, fine-tuning, and training open AI models.

  • Modal

    Modal runs containerized applications on serverless cloud infrastructure, including GPU inference, training, batch jobs, and isolated code sandboxes.

  • Fireworks AI

    Fireworks AI hosts, routes, and trains open and custom models for applications, teams, and research.

  • Truss

    Truss is an open-source CLI for packaging, deploying, and serving machine-learning models on Baseten or your own infrastructure.

  • Cerebras Inference

    Cerebras Inference serves AI models through a cloud API and web playground, with pay-per-token access for developers and reserved options for enterprises.

  • Core42

    Core42 provides sovereign cloud and AI infrastructure for training, deploying and running AI models, including inference through its Compass API.

More from Baseten

  • Truss

    Truss is an open-source CLI for packaging, deploying, and serving machine-learning models on Baseten or your own infrastructure.

Questions about Baseten

Is Baseten free?

Yes. The maker’s pages state that Baseten can be used for free. Read on the maker’s pages on 18 Nov 2026.

How much does Baseten cost?

The plans on the maker’s pricing page: Pay as you go ($0.035 per 1M input tokens (elephant-1)) and Production scale (price on request). These prices were read by web search, not on the maker’s own page: check its pricing page before relying on them. Prices checked on 5 Nov 2026.

Does Baseten have an API?

Yes. The maker’s pages state that Baseten has an API. Read on the maker’s pages on 18 Nov 2026.

Which platforms does Baseten run on?

Baseten runs on Web, CLI and API, as its maker’s pages state. Read on the maker’s pages on 18 Nov 2026.

Is Baseten open source?

The maker’s pages do not present Baseten as open source. Read on the maker’s pages on 18 Nov 2026.

Is Baseten still available?

Yes, as of 18 Nov 2026: its maker’s pages were read that day and carried no notice that Baseten has ended.

What changed recently in Baseten?

The latest entry in its maker’s changelog: 29 Oct 2026, “joey-1 decision model available on Baseten”. Before it: 28 Oct 2026, “elephant-1 and mammoth-1 pricing”. Changelog checked on 13 Nov 2026.

Sources

Not confirmed

Latest version
No current Baseten product version or version number was identified on the pages read.
Official website