Developer Tools

Baseten

AI model deployment and inference platform for production applications.

Visit platform Sign up

What is Baseten

Baseten provides managed model APIs, dedicated deployments and training infrastructure for production AI applications.

Plans

As of September 7, 2026, Basic costs US$0 per month plus pay-as-you-go usage and includes model APIs, training and dedicated deployments. Pro uses custom pricing and adds volume discounts, priority GPU access, dedicated compute, higher API rate limits and Slack, Zoom and support access. Enterprise is also custom priced and can add self-hosting, flexible compute, cloud-commitment support, data residency, security controls and role-based access.

Usage pricing

Current model API examples per million tokens include GLM 5.3 at US$1.40 input, US$0.14 cached input and US$4.40 output; GLM 5.3 Flash at US$0.15, US$0.03 and US$0.50; GPT-OSS 120B at US$0.10 input and US$0.50 output; and Kimi K3 at US$3, US$0.30 and US$15. The API Cost page carries the complete current token-priced catalogue verified in this review.

Published dedicated deployment rates per minute include US$0.01052 for T4, US$0.01414 for L4, US$0.02012 for A10G, US$0.06667 for A100, US$0.10833 for H100 and US$0.16633 for B200. Baseten says usage is billed for compute consumed without idle-time charges.

Official source: Baseten pricing.

Last updated 06-Sep-2026

From AI Provider Index

06 Aug 2026 09:44 AEST · Ronald

Baseten adds NVIDIA Nemotron streaming speech recognition

Baseten has added NVIDIA Nemotron 3.5 ASR Streaming models to its model library, offering English and 40-locale multilingual transcription through NVIDIA NIM. Baseten reports support for 100...

01 Aug 2026 09:12 AEST · Ronald

Baseten Adds Hosted Inkling Small Model API Access

Baseten has added Inkling Small to its hosted Model APIs and dedicated-deployment service. The open-weight mixture-of-experts model has 276 billion total parameters, 12 billion active parameters, a...

31 Jul 2026 09:24 AEST · Ronald

Baseten Launches Distribution Platform for Closed Model Labs

Baseten has launched a distribution and monetisation platform for developers of closed-weight AI models. Baseten for Model Labs combines managed inference, Model Library distribution and commercial...

17 Jul 2026 20:17 AEST · Ronald

Baseten Cuts Wan 2.2 Video Inference Below Three Seconds

Baseten says its optimised Wan 2.2 runtime can generate a video clip in 2.75 seconds, 53.6 times faster than its baseline. A guarded public demo runs until 31 July, while the company acknowledges...

16 Jul 2026 20:26 AEST · Ronald

Baseten Adds NVIDIA Nemotron 3 Embed Models

Baseten has made NVIDIA's Nemotron 3 Embed 8B and 1B models available for dedicated inference. The pair targets enterprise and code retrieval with different balances of accuracy, throughput and...

15 Jul 2026 20:18 AEST · Ronald

Baseten Adds Day-One Hosting for Inkling Multimodal Model

Baseten has added day-one access to Thinking Machines Lab’s Inkling model through its managed Model APIs and Dedicated Inference service. The launch gives developers a hosted route to a very large...