S CostSaver
Sign in
B

BaseTen

baseten · 14 models · synced never

Production model inference infrastructure.

Model Type Input $/MTok Output $/MTok Context
gpt-oss-120b (batch) openai LLM $0.1 $0.5 128K
DeepSeek V4 Flash 0731 deepseek LLM $0.13 $0.26 1.0M
GLM 5.3 Flash (batch) z-ai LLM $0.15 $0.5 1.0M
DeepSeek V4.1 Flash (batch) deepseek LLM $0.3 $1.20 1.0M
Inkling Small (free) thinkingmachines STT $0.5 $1.20 1.0M
Nemotron 3 Ultra (free) nvidia LLM $0.6 $2.40 203K
Kimi K2.6 moonshotai LLM $0.95 $4.00 262K
Kimi K2.7 Code moonshotai LLM $0.95 $4.00 262K
Inkling (free) thinkingmachines STT $1.00 $4.05 1.0M
DeepSeek V4 Pro 0813 deepseek LLM $1.32 $3.96 1.0M
DeepSeek V4 Pro 0423 deepseek LLM $1.74 $3.48 1.0M
GLM 5.2 (free) z-ai LLM $2.10 $6.60 1.0M
GLM 5.3 (batch) z-ai LLM $2.10 $6.60 1.0M
Kimi K3 (batch) moonshotai LLM $3.00 $15.00 1.0M