Ir para o conteúdo
AI.info

AI Tools

Truss

Truss: preços, capacidades, atualizações e alternativas, lidos nas páginas do próprio desenvolvedor.

O site de Truss

Em inglês

Key facts

Price
Paid plans: see pricing Read on baseten.co
Free plan
No Read on baseten.co
Platforms
CLI · API Read on baseten.co
API
Yes
Open source
Yes · MIT Read on github.com
Certifications
SOC 2 Type II · ISO 27001 · GDPR · HIPAA Read on trust.baseten.co
Last update
12 Nov 2026 Read on github.com
Prices checked
12 Nov 2026 Read on baseten.co

Truss helps developers package model code, weights, and dependencies, configure hardware, and deploy models for inference. It supports Python-based ML frameworks and can also launch training jobs; deployments can expose model APIs.

The CLI is open source under the MIT license. Truss itself has no standalone pricing tiers listed on Baseten’s pricing page; hosting and compute on Baseten are billed separately based on usage.

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

Company

Baseten

Features

  • Package model code, weights, and dependencies for deployment
  • Configure model hardware and deployment settings
  • Deploy models to Baseten from the CLI
  • Serve models built with Python ML frameworks
  • Launch training jobs on Baseten GPUs
  • Iterate on development deployments with live reload
  • Open-source software licensed under MIT

Use cases

  • Package a custom model for deployment
  • Deploy an open-source model as an inference API
  • Configure GPU resources for model serving
  • Iterate on model-serving code during development
  • Launch a training job on Baseten infrastructure

Pricing

Paid plans: see pricing

Prices checked
2026-11-12

Production scale

price on request

  • Volume discounts
  • Reserved and priority compute
  • Capacity planning and custom terms
  • Custom regions and support

Model APIs — mammoth-1

$0.10 per 1M input tokens

  • $0.10 per 1M input tokens

Model APIs — elephant-1

$0.035 per 1M input tokens

  • $0.035 per 1M input tokens

Model APIs — joey-1

$0.01 per 1M input tokens

  • $0.01 per 1M input tokens

Model APIs — Beam

$0.40 per 1M input tokens

  • $0.40 per 1M input tokens
  • $0.04 per 1M cache input tokens
  • $1.20 per 1M output tokens

Model APIs — Muse Spark Open

$1.25 per 1M input tokens

  • $1.25 per 1M input tokens
  • $0.15 per 1M cache input tokens
  • $4.25 per 1M output tokens

Model APIs — GLM-5.3 Fast

$2.10 per 1M input tokens

  • $2.10 per 1M input tokens
  • $0.21 per 1M cache input tokens
  • $6.60 per 1M output tokens

Model APIs — GLM-5.3

$1.40 per 1M input tokens

  • $1.40 per 1M input tokens
  • $0.14 per 1M cache input tokens
  • $4.40 per 1M output tokens

Model APIs — GLM-5.3-Flash

$0.15 per 1M input tokens

  • $0.15 per 1M input tokens
  • $0.03 per 1M cache input tokens
  • $0.50 per 1M output tokens

Model APIs — GLM-5.2 Fast

$2.10 per 1M input tokens

  • $2.10 per 1M input tokens
  • $0.21 per 1M cache input tokens
  • $6.60 per 1M output tokens

Capabilities

  • Command line — “Use the Baseten CLI to deploy and manage the package on Baseten with autoscaling and observability.” source
  • API — “The serving configuration is separate from how you deploy it. Deploy a model shows the same model deployed from Explore, from a Truss project with the Baseten CLI, or through the Management API.” source
  • Builds agents and workflows — “Use Chains when a workflow contains multiple models or steps that need different hardware.” source

Latest updates

  • Version 0.18.41rc2

    Enforced health-check thresholds for trt_llm deployments, added --deployment-name for BIS LLM pushes, and added provisional accelerators.

  • Version 0.18.41rc0

    Enforced health-check thresholds for trt_llm deployments and added --deployment-name for BIS LLM pushes.

  • Version 0.18.40

    Added opt-in linked root spans and per-call batch keys, TPU accelerator groundwork, and BEIv3 native no-build encoder serving.

  • Version 0.18.40rc102

    Added opt-in linked root spans and per-call batch keys, TPU accelerator groundwork, and BEIv3 native no-build encoder serving.

  • Version 0.18.40rc101

    Added opt-in linked root spans and per-call batch keys, and TPU accelerator groundwork.

Where it works

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 — “Baseten Data Processing Agreement.pdf” source
  • HIPAA — “Baseten Labs, Inc. HIPAA Report 5.31.26.pdf” source

Alternatives to Truss

  • Baseten

    Baseten provides infrastructure to deploy and run AI models, train models, and build agent workflows using managed inference, APIs, training tools, and sandboxes.

  • RunPod Pods

    RunPod Pods provide dedicated cloud GPUs for AI development, training, fine-tuning, inference, and long-running jobs.

  • Lambda GPU Cloud

    Lambda GPU Cloud rents NVIDIA GPU instances and clusters for training, fine-tuning, and serving AI models.

  • Ludwig

    Open-source framework for training, fine-tuning, evaluating, and serving AI models with YAML configurations.

  • Text Generation Inference

    Text Generation Inference is an open-source toolkit for deploying and serving large language models through an API.

  • Modal

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

More from Baseten

  • Baseten

    Baseten provides infrastructure to deploy and run AI models, train models, and build agent workflows using managed inference, APIs, training tools, and sandboxes.

Questions about Truss

Is Truss free?

No. The maker’s pricing page lists no free plan for Truss. Prices checked on 12 Nov 2026.

How much does Truss cost?

The plans on the maker’s pricing page: Production scale (price on request), Model APIs — mammoth-1 ($0.10 per 1M input tokens), Model APIs — elephant-1 ($0.035 per 1M input tokens), Model APIs — joey-1 ($0.01 per 1M input tokens), Model APIs — Beam ($0.40 per 1M input tokens), Model APIs — Muse Spark Open ($1.25 per 1M input tokens), Model APIs — GLM-5.3 Fast ($2.10 per 1M input tokens), Model APIs — GLM-5.3 ($1.40 per 1M input tokens), Model APIs — GLM-5.3-Flash ($0.15 per 1M input tokens) and Model APIs — GLM-5.2 Fast ($2.10 per 1M input tokens). Prices checked on 12 Nov 2026.

Does Truss have an API?

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

Which platforms does Truss run on?

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

Is Truss open source?

Yes. The code of Truss is published at github.com/basetenlabs/truss under the MIT licence. Read on the maker’s pages on 18 Nov 2026.

Is Truss still available?

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

What changed recently in Truss?

The latest entry in its maker’s changelog: 12 Nov 2026, “Version 0.18.41rc2”. Before it: 12 Nov 2026, “Version 0.18.41rc0”. Changelog checked on 15 Nov 2026.

Sources

Official website