Baseten LLM API pricing

Every model Baseten serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first. Verified against LiteLLM and OpenRouter daily.

Models served

10

on this provider

Cheapest input

$0.10

per 1M tokens

Cheapest output

$0.50

per 1M tokens

Max context

262K

tokens

Model ID
gpt-oss-120bOpenAI131K$0.10$0.50baseten/openai/gpt-oss-120b
Nemotron 120B A12bNVIDIAn/a$0.30$0.75baseten/nvidia/Nemotron-120B-A12B
DeepSeek V3 1DeepSeek164K$0.50$1.50baseten/deepseek-ai/DeepSeek-V3.1
Kimi K2.5Moonshot262K$0.60$3.00baseten/moonshotai/Kimi-K2.5
Kimi K2 ThinkingMoonshot262K$0.60$2.50baseten/moonshotai/Kimi-K2-Thinking
Kimi K2 Instruct 0905Moonshot262K$0.60$2.50baseten/moonshotai/Kimi-K2-Instruct-0905
GLM 4.6Zhipu205K$0.60$2.20baseten/zai-org/GLM-4.6
GLM 4.7Zhipu205K$0.60$2.20baseten/zai-org/GLM-4.7
DeepSeek V3 0324DeepSeek164K$0.77$0.77baseten/deepseek-ai/DeepSeek-V3-0324
GLM 5Zhipu203K$0.95$3.15baseten/zai-org/GLM-5
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI