Baseten
Serverless
Inference platform for open-weight models: per-token Model APIs (GLM, DeepSeek V4, Kimi K3, GPT OSS) behind an OpenAI-compatible endpoint with 1M-token context, tool calling and structured outputs, plus dedicated autoscaling GPU deployments and training for custom models, billed per minute.
Features
OpenAI Compatible
Streaming
Batching
Fine-tuning
Embeddings
Vision
Audio
Function Calling
JSON Mode
Compliance
SOC 2
HIPAA
GDPR
Pricing Model
per token Free tier: Credits for new accounts on the free Basic plan
Details
Models 11
API Base
https://inference.baseten.co/v1 GPU CloudLLM Inference
Model Catalog (11)
| Model | Type | Input $/1M | Output $/1M | Context | Speed | Status |
|---|---|---|---|---|---|---|
| DeepSeek V4 Flash DeepSeek 0731 | llm | $0.130 | $0.260 | 1.0M | — | |
| DeepSeek V4 Pro DeepSeek 0813 | llm | $1.32 | $3.96 | 1.0M | — | |
| DeepSeek V4.1 Flash DeepSeek | llm | $0.300 | $1.20 | 1.0M | — | |
| DeepSeek V4.1 Flash DeepSeek Fast | llm | $0.600 | $2.40 | 1.0M | — | |
| GLM 5.2 Z.ai | llm | $1.40 | $4.40 | 1.0M | — | |
| GLM 5.2 Z.ai Fast | llm | $2.10 | $6.60 | 1.0M | — | |
| GLM 5.3 Z.ai | llm | $1.40 | $4.40 | 1.0M | — | |
| GLM 5.3 Z.ai Fast | llm | $2.10 | $6.60 | 1.0M | — | |
| GLM 5.3 Flash Z.ai | llm | $0.150 | $0.500 | 1.0M | — | |
| GPT OSS 120B OpenAI · 117B MoE (5.1B active) | llm | $0.100 | $0.500 | 131k | — | |
| Kimi K3 Moonshot AI | llm | $3.00 | $15.00 | 1.0M | — |
Baseten API FAQ
Is the Baseten API free?
Yes, Baseten has a free tier: Credits for new accounts on the free Basic plan. Paid usage is billed per model.
What is the cheapest Baseten model?
GPT OSS 120B at $0.10 in / $0.50 out per 1M tokens, based on the 11 models we track for Baseten.
How many models does Baseten offer?
We track 11 Baseten models: 11 LLM.
Is the Baseten API OpenAI-compatible?
Yes. Baseten exposes an OpenAI-compatible endpoint, so you can use the OpenAI SDKs by changing the base URL and API key.