← back 
Baseten
85High-performance LLM inference platform with an OpenAI-compatible endpoint — swap your base URL to access DeepSeek, GLM, Kimi, GPT OSS, and more.
API KeyPay-as-you-goJSONBot Blocking: NoneNo CCopenai-compatibleinferencedeepseekstreamingtool-callingvision
Pros
- + Drop-in OpenAI SDK compatibility — just change base_url and api_key
- + Supports structured outputs, tool calling, streaming, and vision out of the box
- + Access to high-performance open models (DeepSeek, GLM, Kimi) at competitive per-token pricing
Cons
- - Rate limits not publicly documented — must contact support for increases
- - No published OpenAPI spec, so agents can't auto-discover endpoints
Integration
example.py
from openai import OpenAIimport os
client = OpenAI( base_url="https://inference.baseten.co/v1", api_key=os.environ["BASETEN_API_KEY"])
response = client.chat.completions.create( model="deepseek-ai/DeepSeek-V3.1", messages=[{"role": "user", "content": "Hello"}])print(response.choices[0].message.content)Details
- Category
- LLM
- Pricing
- Pay-as-you-go
- Free Tier
- Free credits on sign-up for experimentation
- Rate Limit
- Varies by account tier (req/min + token/min limits, 429 on exceed)
- Verified
- 2026-03-31
Score Breakdown
Base +50
OpenAPI Spec (No) 0
Auth Complexity (API Key) +10
Response Format (JSON) +10
Bot Blocking (None) +10
No Credit Card (Yes) +5
Completely Free (No) 0
Total 85