chore(pricing): Update vertex-ai pricing

[siddharthsambharia-portkey]

🔄 Pricing Update: vertex-ai

📊 Summary (complete_diff mode)

Change Type	Count
➕ Models added	5
🔄 Models updated (merged)	11

➕ New Models

• gemini-2.5-pro-tts
• gemini-2.5-flash-tts
• gemma-4-26b-a4b-it-maas
• gemini-3.1-flash-tts-preview
• veo-3.1-lite-generate-001

🔄 Updated Models

• gemini-2.5-pro
• gemini-2.5-computer-use-preview-10-2025
• gemini-3-pro-preview
• gemini-3-flash-preview
• gemini-3-pro-image-preview
• gemini-3.1-pro-preview
• gemini-3.1-flash-image-preview
• gemini-3.1-flash-lite-preview
• veo-3.0-fast-generate-001
• veo-3.1-fast-generate-001
• multimodalembedding

Model-to-Pricing-Page Mapping

Google – Gemini (text/multimodal)

Model ID	Publisher / Section	Source	Notes
gemini-2.5-pro	Google – Gemini 2.5 Pro	API	Standard ≤200K prices used; long-context (>200K): input $2.50, output $15
gemini-2.5-flash	Google – Gemini 2.5 Flash	API	web_search $35/1K → 3.5¢; enterprise $45/1K → 4.5¢
gemini-2.5-flash-lite	Google – Gemini 2.5 Flash-Lite	API	—
gemini-2.5-flash-preview-09-2025	Google – Gemini 2.5 Flash	API	Preview alias; priced same as gemini-2.5-flash
gemini-2.5-flash-lite-preview-09-2025	Google – Gemini 2.5 Flash-Lite	API	Preview alias; priced same as gemini-2.5-flash-lite
gemini-2.5-computer-use-preview-10-2025	Google – Gemini 2.5 Pro (Computer Use)	API	Matched to Gemini 2.5 Pro pricing row
gemini-2.5-flash-image	Google – Gemini 2.5 Flash Image	API	Image output model; image_token $30/1M added
gemini-2.5-pro-tts	Google – Gemini	API – price not found	TTS model; no dedicated pricing row; added with price 0
gemini-2.5-flash-tts	Google – Gemini	API – price not found	TTS model; no dedicated pricing row; added with price 0
gemini-2.0-flash-001	Google – Gemini 2.0 Flash	API	Batch pricing added; web_search 3.5¢
gemini-2.0-flash-lite-001	Google – Gemini 2.0 Flash-Lite	API	Batch pricing added
gemma-4-26b-a4b-it-maas	Google – Gemma 4 26B	API	MaaS Gemma; priced at $0.15/$0.60 per the pricing page
gemini-3-pro-preview	Google – Gemini 3 Pro Preview	API	Matched to Gemini 3 Pro Preview row
gemini-3-flash-preview	Google – Gemini 3 Flash Preview	API	Matched to Gemini 3 Flash Preview row
gemini-3-pro-image-preview	Google – Gemini 3 Pro Image Preview	API	Image output model; image_token $30/1M
gemini-3.1-pro-preview	Google – Gemini 3.1 Pro Preview	API	—
gemini-3.1-flash-image-preview	Google – Gemini 3.1 Flash Image Preview	API	Image output model; image_token $30/1M
gemini-3.1-flash-lite-preview	Google – Gemini 3.1 Flash-Lite Preview	API	—
gemini-3.1-flash-tts-preview	Google – Gemini	API – price not found	TTS preview; no pricing row; added with price 0

Google – Imagen

Model ID	Publisher / Section	Source	Notes
imagen-4.0-ultra-generate-001	Google – Imagen 4.0 Ultra Generate	API	$0.06/image
imagen-4.0-generate-001	Google – Imagen 4.0 Generate	API	$0.04/image
imagen-4.0-fast-generate-001	Google – Imagen 4.0 Fast Generate	API	$0.02/image
imagen-3.0-generate-002	Google – Imagen 3.0 Generate	API	$0.04/image
imagen-3.0-capability-001	Google – Imagen 3.0 Capability	API	Capability model; uses imagen-3.0-generate pricing ($0.04/image)
imagen-3.0-capability-002	Google – Imagen 3.0 Capability	API	Capability model; uses imagen-3.0-generate pricing ($0.04/image)

Google – Veo (video)

Model ID	Publisher / Section	Source	Notes
veo-2.0-generate-001	Google – Veo 2.0	API	$0.50/s video; 8s default
veo-3.0-generate-001	Google – Veo 3.0	API	$0.20/s video-only 720p/1080p; 8s default
veo-3.0-fast-generate-001	Google – Veo 3.0 Fast	API	$0.08/s video-only 720p; 8s default
veo-3.1-generate-001	Google – Veo 3.1	API	$0.20/s video-only 720p/1080p; 8s default
veo-3.1-fast-generate-001	Google – Veo 3.1 Fast	API	$0.08/s video-only 720p; 8s default
veo-3.1-lite-generate-001	Google – Veo 3.1 Lite	API	$0.03/s video-only 720p; 8s default

Google – Embedding

Model ID	Publisher / Section	Source	Notes
gemini-embedding-001	Google – Gemini Embedding	API	$0.00015/1K tokens
text-embedding-005	Google – Text Embedding (excl. Gemini)	API	$0.000025/1K chars (as per_thousand_tokens)
text-multilingual-embedding-002	Google – Text Embedding (excl. Gemini)	API	$0.000025/1K chars
textembedding-gecko	Google – Text Embedding (excl. Gemini)	API	Legacy; same family pricing $0.000025/1K
text-embedding-large-exp-03-07	Google – Text Embedding (excl. Gemini)	API	Experimental; no dedicated row; shares text-embedding pricing
multimodalembedding	Google – Multimodal Embedding	API	Text $0.0002/1K + image $0.0001 + video tiers

Anthropic – Claude

Model ID	Publisher / Section	Source	Notes
claude-opus-4-1@20250805	Anthropic – Claude Opus 4.1	API	Pinned date version; input $15, output $75
claude-sonnet-4-5@20250929	Anthropic – Claude Sonnet 4.5	API	Pinned date version; ≤200K standard pricing
claude-haiku-4-5@20251001	Anthropic – Claude Haiku 4.5	API	Pinned date version
claude-opus-4-5@20251101	Anthropic – Claude Opus 4.5	API	Pinned date version; input $5, output $25
claude-opus-4-6	Anthropic – Claude Opus 4.6	API	@default stripped; input $5, output $25
claude-sonnet-4-6	Anthropic – Claude Sonnet 4.6	API	@default stripped
claude-opus-4-7	Anthropic – Claude Opus 4.7	API	@default stripped; input $5, output $25

OpenAI

Model ID	Publisher / Section	Source	Notes
gpt-oss-120b-maas	OpenAI – GPT OSS 120B	API	MaaS; input $0.09, output $0.36

Meta – Llama

Model ID	Publisher / Section	Source	Notes
llama-3.3-70b-instruct-maas	Meta – Llama 3.3 70B	API	MaaS; $0.72/$0.72
llama-4-maverick-17b-128e-instruct-maas	Meta – Llama 4 Maverick	API	MaaS; $0.35/$1.15

Mistral

Model ID	Publisher / Section	Source	Notes
mistral-small-2503	Mistral – Mistral Small 3.1	API	$0.10/$0.30
mistral-medium-3	Mistral – Mistral Medium 3	API	$0.40/$2.00
codestral-2	Mistral – Codestral 2	API	$0.30/$0.90

DeepSeek

Model ID	Publisher / Section	Source	Notes
deepseek-v3.1-maas	DeepSeek – DeepSeek-V3.1	API	MaaS; cache_read $0.06/1M
deepseek-v3.2-maas	DeepSeek – DeepSeek-V3.2	API	MaaS; cache_read $0.056/1M
deepseek-r1-0528-maas	DeepSeek – DeepSeek-R1-0528	API	MaaS; $1.35/$5.40

Qwen

Model ID	Publisher / Section	Source	Notes
qwen3-235b-a22b-instruct-2507-maas	Qwen – Qwen3-235B	API	MaaS; $0.22/$0.88
qwen3-coder-480b-a35b-instruct-maas	Qwen – Qwen3 Coder 480B	API	MaaS; cache_read $0.022/1M
qwen3-next-80b-a3b-instruct-maas	Qwen – Qwen3-Next-80B Instruct	API	MaaS; $0.15/$1.20
qwen3-next-80b-a3b-thinking-maas	Qwen – Qwen3-Next-80B Thinking	API	MaaS; $0.15/$1.20

Moonshot / Kimi

Model ID	Publisher / Section	Source	Notes
kimi-k2-thinking-maas	Moonshot – Kimi K2 Thinking	API	MaaS; cache_read $0.06/1M

MiniMax

Model ID	Publisher / Section	Source	Notes
minimax-m2-maas	MiniMax – MiniMax M2	API	MaaS; cache_read $0.03/1M

ZAI.org – GLM

Model ID	Publisher / Section	Source	Notes
glm-4.7-maas	ZAI.org – GLM-4.7	API	MaaS; $0.60/$2.20
glm-5-maas	ZAI.org – GLM-5	API	MaaS; cache_read $0.10/1M

---

Excluded Models (not added to pricing)

Model / Pattern	Publisher	Reason
gemini-live-2.5-flash-native-audio	Google	Gemini Live streaming — excluded
lyria-* (lyria-002, lyria-3-pro-preview, lyria-3-clip-preview)	Google	Music generation — excluded
model-optimizer-*	Google	Meta-endpoint — excluded
imagegeneration	Google	Legacy superseded model — excluded
virtual-try-on-001	Google	Retail product model — excluded per google.md
shieldgemma2	Google	Guard model — excluded
chirp-2, chirp-3	Google	Audio transcription — excluded
translate-llm	Google	Non-generative translation — excluded
weathernext, weather-next-v2	Google	Non-generative forecast — excluded
All self-deploy Gemma/PaLM/Codey/etc.	Google	Self-deploy, non-generative, or fine-tuning only
All traditional CV/NLP models	Google	Non-generative ML
pretrained-ocr, pretrained-form-parser	Google	OCR — excluded
image-segmentation-001, sam3	Google/Meta	Non-generative segmentation — excluded
jamba-large-1.6	AI21	Self-deploy (has_deploy: true, no -maas) — excluded
qwen-image	Qwen	Excluded by policy
glm-image, glm-ocr	ZAI.org	glm-image excluded by policy; glm-ocr is OCR
glm-4.7, glm-5, glm-4.5	ZAI.org	Self-deploy — excluded
kimi-k2, kimi-k2-5	Moonshot	Self-deploy — excluded
minimax-m2	MiniMax	Self-deploy — excluded
deepseek-r1, deepseek-v3, deepseek-v4, deepseek-v3-1, deepseek-v3-2	DeepSeek	Self-deploy — excluded
deepseek-ocr-maas, deepseek-ocr, deepseek-ocr-2	DeepSeek	OCR — excluded
All self-deploy Qwen variants	Qwen	Self-deploy (no -maas) — excluded
mistral-ocr-2505	Mistral	OCR — excluded
ministral-3, mistral-large-3, codestral-2501-self-deploy	Mistral	Self-deploy — excluded
llama-guard, prompt-guard	Meta	Guard models — excluded
sam3	Meta	Non-generative segmentation — excluded
All self-deploy Llama variants	Meta	Self-deploy (no -maas) — excluded
Non-generative Meta models (roberta, imagebind, nllb, faster-rcnn, etc.)	Meta	Non-generative ML — excluded
gpt-oss-20b, clip-*, openclip, whisper-*	OpenAI	gpt-oss-20b self-deploy; clip non-generative; whisper transcription
xAI Grok models	xAI	Pricing page only — not returned by get_vertex_models; not added

---

Generated by Pricing Agent on 2026-04-27