Nebius Token Factory public model catalog (per-model USD per 1M tokens), fetched 2026-10-16

Public markdown catalog. Page states the authoritative machine-readable source is /api/public/models_info and this markdown is the reading view. Representative rows extracted 2026-10-16: openai/gpt-oss-120b input 0.15 / output 0.60, context 131k, region eu-north1; Qwen/Qwen3-235B-A22B-Instruct-2507 0.20/0.60, 262k, eu-north1; Qwen/Qwen3-30B-A3B-Instruct-2507 0.10/0.30, 262k, eu-north1; google/gemma-3-27b-it 0.10/0.30, 110k, eu-north1; deepseek-ai/DeepSeek-V4-Flash-0731 0.14/0.28, 1024k, us-central1; deepseek-ai/DeepSeek-V4-Pro 1.75/3.50, uk-south1. No meta-llama/Llama-3.3-70B-Instruct row on this catalog view (the Oct-14 record listed it as indicative). Regions named on the catalog: eu-north1, eu-west2, us-north1, us-central1, uk-south1.