AWS AssumeRole authentication
Baseten can now assume an IAM role in your AWS account to pull private base images from Amazon ECR and mirror model weights from Amazon S3 during builds.
Aug 28, 2026GLM 5.3 available on Baseten
GLM 5.3, Z.ai’s latest flagship model, is now available through Baseten Model APIs and Loops. It has a 1M-token context window and defaults to high reasoning. Set reasoning_effort to low, high, or...
Aug 26, 2026GLM 5.3 Flash available on Baseten
GLM 5.3 Flash is now available through Baseten Model APIs. Send requests to zai-org/GLM-5.3-Flash through our OpenAI-compatible endpoint with your Baseten API key.
Aug 25, 2026Autoscaling schedules
Autoscaling schedules are now generally available. A schedule changes an environment's autoscaling settings on a defined window, so you can pre-warm capacity before traffic arrives.
Aug 19, 2026Runtime OIDC
You can now authenticate to OIDC-compatible cloud providers without storing long-lived credentials. Set runtime.oidc.enabled: true in your Truss config and Baseten mounts a short-lived token into the...
Aug 14, 2026DeepSeek V4 Pro 0813 available on Baseten
DeepSeek V4 Pro 0813 is now available through Baseten Model APIs. Send requests to deepseek-ai/DeepSeek-V4-Pro-0813 through our OpenAI-compatible endpoint with your Baseten API key.
Jul 30, 2026Inkling Small available on Baseten
Inkling Small is now available through Baseten Model APIs. Send requests to thinkingmachines/inkling-small through our OpenAI-compatible endpoint with your Baseten API key. Dedicated deployments are...
Jul 29, 2026Introducing Baseten for Model Labs
Baseten for Model Labs gives labs the infrastructure to bring models to market without building their own serving and distribution systems.
Jul 27, 2026Kimi K3 available on Baseten
You can start sending requests to Kimi K3 today through our Model APIs by calling the OpenAI-compatible endpoint with your Baseten API key. For larger workloads, dedicated deployments are available.
Jul 23, 2026GLM 5.2 Fast available on Baseten
GLM 5.2 Fast is the first model in our new Fast tier on Model APIs: the same GLM 5.2 model weights served on dedicated capacity engineered for higher sustained per-user throughput, built for agentic...