Novita AI serverless-endpoints pricing table (per-1M-token list prices)
database
Fields
id
sources/svc-src-novita-pricing-page-2026-10-14Publisher
Novita AI
Kind
database
Accessed
2026-10-14
notes
Fetched 2026-10-14. Transcribed: GLM 4.5 Air $0.13/$0.85 (128k); GLM 4.7 Flash $0.07/$0.40; GLM 4.6 $0.55/$2.20; GLM 5.3 Flash $0.15/$0.50; Kimi K3 $3.00/$15.00; DeepSeek V4.1 Flash $0.30/$1.20; DeepSeek R1 0528 $0.70/$2.50; Baidu ERNIE-4.5-21B-A3B $0.07/$0.28; Llama-3-8B-Stheno-v3.2 $0.05/$0.05. Batch inference 50% off input and output for supported models. OpenRouter's routing page shows NovitaAI serving meta-llama/llama-3.3-70b-instruct at $0.135/$0.40, 0.58s P50 latency, 41 tps on the same date.
Notes
Fetched 2026-10-14. Transcribed: GLM 4.5 Air $0.13/$0.85 (128k); GLM 4.7 Flash $0.07/$0.40; GLM 4.6 $0.55/$2.20; GLM 5.3 Flash $0.15/$0.50; Kimi K3 $3.00/$15.00; DeepSeek V4.1 Flash $0.30/$1.20; DeepSeek R1 0528 $0.70/$2.50; Baidu ERNIE-4.5-21B-A3B $0.07/$0.28; Llama-3-8B-Stheno-v3.2 $0.05/$0.05. Batch inference 50% off input and output for supported models. OpenRouter's routing page shows NovitaAI serving meta-llama/llama-3.3-70b-instruct at $0.135/$0.40, 0.58s P50 latency, 41 tps on the same date.
Cross-references
This record references no other records.