Baseten Updates & Release Notes

GLM 4.7, Kimi K2.7, Kimi K2.6, Inkling, Inkling Small, and DeepSeek v4 Pro will be deprecated at 5pm PT September 25th.

At that time the model IDs will become inactive and return an error for all requests. As open source models advance rapidly, we prioritize serving the highest quality models and deprecate models when stronger alternatives are available.

We recommend the following models as alternatives, all of which offer superior intelligence for each specific use case. Just swap in the new Model ID(s) prior to the deprecation date.

Training jobs can now use OIDC or AWS AssumeRole during setup to pull private container images and download model weights or training data without storing long-lived cloud credentials in Baseten.

OIDC supports Amazon ECR and S3, Google Artifact Registry and Container Registry, and Google Cloud Storage. Training OIDC tokens let you scope access to your Baseten organization, team, training project, or individual job.

For AWS resources, you can use AWS AssumeRole without registering an OIDC provider. Baseten assumes an IAM role in your account using your organization's unique external ID. AWS AssumeRole supports private images in Amazon ECR and weights or data in Amazon S3.

For setup instructions, see OIDC authentication, AWS AssumeRole, private training images, and weights and data authentication.

DeepSeek V4.1 Flash is now available through Baseten Model APIs. The 552B-parameter multimodal successor to DeepSeek V4 Flash 0731, it is purpose-built for agentic, coding workflows, and has reasoning and tool calling built in.

Send requests to deepseek-ai/DeepSeek-V4.1-Flash through our OpenAI-compatible endpoint with your Baseten API key:

curl https://inference.baseten.co/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $BASETEN_API_KEY" \
-d '{
"model": "deepseek-ai/DeepSeek-V4.1-Flash",
"messages": [
{"role": "user", "content": "Explain the Navier Stokes smoothness problem."}
],
"reasoning_effort": "high"
}'

For more information, see our docs.

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.

AssumeRole uses short-lived AWS STS credentials and a unique external ID for your Baseten organization. You can grant access through a native IAM trust policy without registering an OIDC provider or storing long-lived AWS credentials in Baseten.

For example, you can set

auth_method: AWS_ASSUME_ROLE

in your Truss configuration:

weights:
  -
    source:
      "s3://my-bucket/models/custom-weights"
    mount_location:
      "/models/custom"
    auth:
      auth_method:
      AWS_ASSUME_ROLE
      aws_assume_role_arn:
      arn:aws:iam::<account-id>:role/baseten-access
      aws_assume_role_region:
      us-west-2

For more information, see our docs.

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 max to control reasoning depth.

Send requests to zai-org/GLM-5.3 through Baseten’s OpenAI-compatible endpoint:

curl https://inference.baseten.co/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $BASETEN_API_KEY" \
-d '{
  "model": "zai-org/GLM-5.3",
  "messages": [{
    "role": "user",
    "content": "What is large-scale asynchronous training?"
  }]
}'

Or get started with Loops and fine-tune the model.

For more information, see our docs for Model APIs and Loops for fine-tuning.

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.

GLM 5.3 Flash is Z.ai's latest model with a 1M-token context window, vision, and reasoning. Reasoning defaults to high and can be steered with reasoning_effort (low, high, max).

curl https://inference.baseten.co/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $BASETEN_API_KEY" \
-d '{
  "model": "zai-org/GLM-5.3-Flash",
  "messages": [{
    "role": "user",
    "content": "What is gradient descent?"
  }]
}'

For more information, see our docs or for dedicated inference see the GLM 5.3 Flash deployment.

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.

GLM 5.3 Flash is Z.ai's latest model with a 1M-token context window, vision, and reasoning. Reasoning defaults to high and can be steered with reasoning_effort (low, high, max).

curl https://inference.baseten.co/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $BASETEN_API_KEY" \
-d '{
  "model": "zai-org/GLM-5.3-Flash",
  "messages": [{
    "role": "user",
    "content": "What is gradient descent?"
  }]
}'

For more information, see our docs or for dedicated inference see the GLM 5.3 Flash deployment.

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.

Choose a recurring daily or hourly window for predictable traffic, or a one-time window between two absolute date-times for planned events like launches, load tests, and migrations. While a window is active, the environment runs the schedule's settings; outside every window, it runs the environment's default configuration.

Manage schedules from the Baseten dashboard, or through the Management API:

curl -X PATCH "https://api.baseten.co/v1/models/{model_id}/environments/{env_name}" \
-H "Authorization: Api-Key $BASETEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"autoscaling_schedule_settings": {
"timezone": "America/Los_Angeles",
"schedules": [
{
"cadence": "ONE_TIME",
"name": "Launch day scale-up",
"enabled": true,
"start_at": "2026-09-01T16:00:00Z",
"end_at": "2026-09-01T20:00:00Z",
"autoscaling_settings": {
"min_replica": 4, "max_replica": 16,
}
}
]
}
}'

For more information, see our docs.

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 container, refreshing it at least 5 minutes before it expires.

model_name:
  oidc-enabled
python_version:
  py313
runtime:
  oidc:
    enabled:
      true

Your code exchanges the token with the provider directly, so any OIDC-supporting provider works.

For more information, see our docs.

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.

curl https://inference.baseten.co/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $BASETEN_API_KEY" \
-d '{
"model": "deepseek-ai/DeepSeek-V4-Pro-0813",
"messages": [
  {"role": "system", "content": "You are a helpful assistant"},
  {"role": "user", "content": "Hello"}
],
"reasoning_effort": "high",
"thinking": {"type": "enabled"}
}'

For more information, see our docs.

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 also available for larger workloads.

Inkling Small is Thinking Machines Lab’s open-weights, 276B-parameter mixture-of-experts model with 12B active parameters. It retains Inkling’s 1M-token context window, native text, image, and audio inputs, tool calling, structured outputs, and controllable reasoning in a smaller model designed for workloads where latency and inference cost matter. Thinking Machines reports comparable performance to Inkling at roughly one-quarter its size.

curl https://inference.baseten.co/v1/chat/completions \
-H "Authorization: Bearer $BASETEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "model": "thinkingmachines/inkling-small",
  "messages": [
    {
      "role": "user",
      "content": "Compare sparse and dense transformer architectures."
    }
  ],
  "reasoning_effort": "medium"
}'

For supported reasoning settings and multimodal request examples, see the docs.

Baseten for Model Labs gives labs the infrastructure to bring models to market without building their own serving and distribution systems.

• Frontier Gateway: Run a production-ready API under your own brand. Manage customer credentials, model access, rate limits, usage limits, and billing events across models hosted on Baseten, external providers, or OpenAI-compatible endpoints.
• Distribution Platform: Publish your models to Baseten customers as shared Model APIs, dedicated deployments, or both. Baseten manages customer billing while protecting your model artifacts.

Both run on Baseten’s, so your team can focus on model research while Baseten handles serving and distribution.

To get started, reach out to us or for more information, see our docs.