Google Cloud Vertex AI generative AI pricing, open-model rows, fetched 2026-10-16
spec-sheet
Fields
id
sources/svc-src-gcp-vertex-genai-pricing-2026-10-16Publisher
Google Cloud
Kind
spec-sheet
Accessed
2026-10-16
notes
Partner-model section, USD per 1M tokens, extracted 2026-10-16. Llama 3.3 70B: input 0.72, output 0.72, batch input 0.36, batch output 0.36. Llama 4 Scout 0.25/0.70 (batch 0.125/0.35); Llama 4 Maverick 0.35/1.15 (batch 0.175/0.575). gpt-oss-120b 0.09/0.36 (batch 0.045/0.18); gpt-oss-20b 0.07/0.25. DeepSeek-V3.2 0.56/1.68 (cache hit 0.056); DeepSeek-V3.1 0.60/1.70. Qwen3-235B-A22B-Instruct-2507 0.22/0.88. The Llama 3.3 70B on-demand rate matches the 2026-10-14 OpenRouter Google Vertex row ($0.72/$0.72).
Notes
Partner-model section, USD per 1M tokens, extracted 2026-10-16. Llama 3.3 70B: input 0.72, output 0.72, batch input 0.36, batch output 0.36. Llama 4 Scout 0.25/0.70 (batch 0.125/0.35); Llama 4 Maverick 0.35/1.15 (batch 0.175/0.575). gpt-oss-120b 0.09/0.36 (batch 0.045/0.18); gpt-oss-20b 0.07/0.25. DeepSeek-V3.2 0.56/1.68 (cache hit 0.056); DeepSeek-V3.1 0.60/1.70. Qwen3-235B-A22B-Instruct-2507 0.22/0.88. The Llama 3.3 70B on-demand rate matches the 2026-10-14 OpenRouter Google Vertex row ($0.72/$0.72).
Cross-references
This record references no other records.