Baseten

Baseten is a production inference platform for deploying and serving custom and pre-trained ML models. Offers a Model APIs catalog with OpenAI-compatible endpoints (DeepSeek, Qwen, GLM, Nemotron), dedicated deployments via Truss, autoscaling GPU compute, async/queue inference, training, chains (multi-model workflows), and management APIs.

3 APIs 0 Features

AIMLInferenceDeploymentMLOpsOpenAI CompatibleAnthropic CompatibleTruss

APIs

Baseten LLM Inference API

OpenAI-compatible chat completions for Baseten's Model APIs catalog (DeepSeek V4, Qwen, GLM, Nemotron, etc.). Per-million-token pricing.

Baseten Anthropic-Compatible Messages API

Anthropic Messages-compatible inference for compatible Model APIs models.

Baseten Management & Async API

Deployment management, async/queued inference, chain calls (multi-model workflows), training, dedicated-deployment lifecycle, async result polling, and webhook delivery.

Collections

Baseten LLM Inference API

OPEN

Baseten Anthropic-Compatible Inference API

OPEN

Pricing Plans

Baseten Plans Pricing

1 plans

PLANS

Rate Limits

Baseten Rate Limits

1 limits

RATE LIMITS

FinOps

Baseten Finops

FINOPS

JSON Structure

Baseten Structure

0 properties

JSON STRUCTURE

Resources

👥

GitHubOrganization

Sources

opencollection: 1.0.0
info:
  name: Baseten Anthropic-Compatible Inference API
  version: 1.0.0
request:
  auth:
    type: apikey
    key: Authorization
    value: '{{Authorization}}'
    placement: header
items:
- info:
    name: Messages
    type: folder
  items:
  - info:
      name: Create a message
      type: http
    http:
      method: POST
      url: https://inference.baseten.co/v1/messages
      body:
        type: json
        data: '{}'
    docs: Creates a response message for the provided conversation. Compatible with the Anthropic Messages API, so the Anthropic
      SDK works against this endpoint by changing `base_url` and overriding the default `x-api-key` header with `Authorization`.
bundled: true