chore(pricing): Update vertex-ai pricing

[sivadurga-d]

🔄 Pricing Update: vertex-ai

📊 Summary

Change Type	Count
➕ Models added	56
🔄 Prices updated	4

➕ New Models

• gemini-3.1-flash-image-preview
• gemini-2.5-pro-computer-use-preview
• gemini-2.5-flash-live-api
• gemini-2.0-flash-image-generation
• gemini-2.0-flash-live-api
• gemini-1.5-flash
• gemini-1.5-pro
• imagen-4-ultra
• imagen-4
• imagen-4-fast
• imagen-3
• imagen-3-fast
• imagen-2
• imagen-1
• veo-3.1
• veo-3.1-fast
• veo-3
• veo-3-fast
• veo-2
• multimodalembedding
• ... and 36 more

🔄 Updated Models (price changes)

Model	Request (old → new)	Response (old → new)
gemini-1.0-pro	0.00005 → 0.0000125	0.00015 → 0.0000375
text-embedding-004	0.00001 → 0.000000015	0 → 0
text-embedding-005	0.00001 → 0.000000015	0 → 0
text-multilingual-embedding-002	0.00001 → 0.0000025	0 → 0

📋 Model → Pricing Page Mapping (for review)

Google Models

Model ID	Pricing Page Section	Notes
gemini-3.1-pro-preview	Gemini 3.1 Pro Preview (Standard)	Input/output + cache read + image output token
gemini-3.1-flash-image-preview	Gemini 3.1 Flash Image Preview (Standard)	Input/output + image output token
gemini-3-pro-preview	Gemini 3 Pro Preview (Standard)	Input/output + cache read + image output token
gemini-3-flash-preview	Gemini 3 Flash Preview (Standard)	Input/output + cache read + audio input
gemini-2.5-pro	Gemini 2.5 Pro (Standard)	Input/output + cache write/read
gemini-2.5-pro-computer-use-preview	Gemini 2.5 Pro Computer Use-Preview (Standard)	Input/output
gemini-2.5-flash	Gemini 2.5 Flash (Standard)	Input/output + cache write/read + audio + image token
gemini-2.5-flash-live-api	Gemini 2.5 Flash Live API	Input/output text/audio/image tokens
gemini-2.5-flash-lite	Gemini 2.5 Flash Lite (Standard)	Input/output + cache write/read + audio
gemini-2.0-flash	Gemini 2.0 Flash	Input/output + batch + audio
gemini-2.0-flash-image-generation	Gemini 2.0 Flash Image Generation	Input/output + audio/image + image token
gemini-2.0-flash-live-api	Gemini 2.0 Flash Live API	Input/output text/audio/image tokens
gemini-2.0-flash-lite	Gemini 2.0 Flash Lite	Input/output + batch + audio
gemini-1.5-flash	Gemini 1.5 Flash	Character-based pricing
gemini-1.5-pro	Gemini 1.5 Pro	Character-based pricing
gemini-1.0-pro	Gemini 1.0 Pro	Character-based pricing

Google Imagen Models

Model ID	Pricing Page Section	Notes
imagen-4-ultra	Imagen 4 Ultra	$0.06/image
imagen-4	Imagen 4	$0.04/image
imagen-4-fast	Imagen 4 Fast	$0.02/image
imagen-3	Imagen 3	$0.04/image
imagen-3-fast	Imagen 3 Fast	$0.02/image
imagen-2	Imagen 2	$0.02/image
imagen-1	Imagen 1	$0.02/image

Google Veo Models

Model ID	Pricing Page Section	Notes
veo-3.1	Veo 3.1	$0.20/sec (720p/1080p), $0.40/sec (4k)
veo-3.1-fast	Veo 3.1 Fast	$0.10/sec (720p/1080p), $0.30/sec (4k)
veo-3	Veo 3	$0.20/sec (720p/1080p)
veo-3-fast	Veo 3 Fast	$0.10/sec (720p/1080p)
veo-2	Veo 2	$0.50/sec (720p)

Google Embedding Models

Model ID	Pricing Page Section	Notes
text-embedding-004	Gemini Embedding	Input + batch
text-embedding-005	Gemini Embedding	Input + batch
text-multilingual-embedding-002	Embeddings for Text	Character-based
multimodalembedding	Embeddings for Multimodal: Text	Character-based
multilingual-e5-small	multilingual-e5-small	Input + batch
multilingual-e5-large	multilingual-e5-large	Input + batch

Anthropic Claude Models (Global Region)

Model ID	Pricing Page Section	Notes
claude-opus-4.6	Claude Opus 4.6 (Global)	Input/output + batch + cache write/read
claude-opus-4.5	Claude Opus 4.5 (Global)	Input/output + batch + cache write/read
claude-sonnet-4.6	Claude Sonnet 4.6 (Global)	Input/output + batch + cache write/read
claude-sonnet-4.5	Claude Sonnet 4.5 (Global)	Input/output + batch + cache write/read
claude-haiku-4.5	Claude Haiku 4.5 (Global)	Input/output + batch + cache write/read
claude-opus-4.1	Claude Opus 4.1 (Uniform)	Input/output + batch + cache write/read
claude-opus-4	Claude Opus 4 (Uniform)	Input/output + batch + cache write/read
claude-sonnet-4	Claude Sonnet 4 (Uniform)	Input/output + batch + cache write/read
claude-3-haiku	Claude 3 Haiku (Uniform)	Input/output + cache write/read
claude-3.5-haiku	Claude 3.5 Haiku (Uniform)	Input/output + batch + cache write/read
claude-3.7-sonnet	Claude 3.7 Sonnet (Uniform)	Input/output + batch + cache write/read

OpenAI Models

Model ID	Pricing Page Section	Notes
gpt-oss-120b	gpt-oss-120b	Input/output + batch
gpt-oss-20b	gpt-oss-20b	Input/output + batch + cache hit

Meta Llama Models

Model ID	Pricing Page Section	Notes
llama-3.1-405b	Llama 3.1 405B	Input/output
llama-3.3-70b	Llama 3.3 70B	Input/output + batch
llama-4-scout	Llama 4 Scout	Input/output + batch
llama-4-maverick	Llama 4 Maverick	Input/output + batch

Mistral AI Models

Model ID	Pricing Page Section	Notes
mistral-ocr-25.05	Mistral OCR (25.05)	Input/output
mistral-medium-3	Mistral Medium 3	Input/output
mistral-small-3.1-25.03	Mistral Small 3.1 (25.03)	Input/output
codestral-2	Codestral 2	Input/output

Other Partner Models

Model ID	Pricing Page Section	Notes
jamba-1.5-large	Jamba 1.5 Large (Deprecated)	Input/output
jamba-1.5-mini	Jamba 1.5 Mini (Deprecated)	Input/output
deepseek-v3.1	DeepSeek-V3.1	Input/output + cache hit + batch
deepseek-v3.2	DeepSeek-V3.2	Input/output + cache hit + batch
deepseek-r1-0528	DeepSeek-R1 (0528)	Input/output + batch
deepseek-ocr	DeepSeek-OCR	Input/output
minimax-m2	MiniMax-M2	Input/output + cache hit
kimi-k2-thinking	Kimi-K2-Thinking	Input/output + cache hit
qwen3-next-80b-thinking	Qwen3-Next-80B-Thinking	Input/output
qwen3-next-80b-instruct	Qwen3-Next-80B-Instruct	Input/output
qwen3-coder-480b-a35b-instruct	Qwen3-Coder-480B-A35B-Instruct	Input/output + cache hit + batch
qwen3-235b-a22b-instruct-2507	Qwen3-235B-A22B-Instruct-2507	Input/output + batch
glm-4.7	GLM-4.7	Input/output
glm-5	GLM-5	Input/output + cache hit

Total: 69 models processed

---

Generated by Pricing Agent on 2026-03-01