Provider

Baseten

19 Models · 25 Prices · Cheapest on 1 · Uptime 99.8% · updated 2026-08-05 00:15 UTC

Trust signals · SLA · model-version transparency · pricing stability · quantization-degradation · incident response · data privacy — measured by TKX probe (activating).

About

Baseten is an AI inference provider that utilizes machine learning to serve 15 models via official/openrouter, offering a platform for deploying and managing AI models in a variety of applications.

AI-generated summary from public information — is this yours? Claim & edit

Models served

Model$ in /1M$ out /1MCheapestRouter / SourceEvidence
DeepSeek-V4-Flash-0731 $0.130$0.260 HuggingFace Router API-measured
gpt-oss-120b $0.100$0.500 Pricebook (LiteLLM) Official list
Nemotron-120B-A12B $0.300$0.750 Pricebook (LiteLLM) Official list
MiniMax-M2.5 $0.300$1.20 Pricebook (LiteLLM) Official list
Inkling-Small $0.500$1.20 HuggingFace Router API-measured
DeepSeek-V3.1 $0.500$1.50 Pricebook (LiteLLM) Official list
DeepSeek-V3-0324 $0.770$0.770 Pricebook (LiteLLM) Official list
GLM-4.7 $0.600$2.20 Pricebook (LiteLLM) Official list
GLM-4.6 $0.600$2.20 Pricebook (LiteLLM) Official list
Kimi-K2-Thinking $0.600$2.50 Pricebook (LiteLLM) Official list
Kimi-K2-Instruct-0905 $0.600$2.50 Pricebook (LiteLLM) Official list
Kimi-K2.5 $0.600$3.00 Pricebook (LiteLLM) Official list
GLM-5 $0.950$3.15 Pricebook (LiteLLM) Official list
Kimi-K2.7-Code $0.950$4.00 HuggingFace Router API-measured
Kimi-K2.6 $0.950$4.00 HuggingFace Router API-measured
Inkling $1.00$4.05 HuggingFace Router API-measured
GLM-5.2 $1.40$4.40 HuggingFace Router API-measured
DeepSeek V4 Pro $1.74$3.48 OpenRouter API-measured
Kimi-K3 $3.00$15.00 HuggingFace Router API-measured

Related analysis

← All providers