chore(pricing): Update vertex-ai pricing

[siddharthsambharia-portkey]

🔄 Pricing Update: vertex-ai

📊 Summary (complete_diff mode)

Change Type	Count
➕ Models added	0
🔄 Models updated (merged)	7

🔄 Updated Models

• gemini-3.1-pro-preview
• gemini-3.1-flash-image-preview
• gemini-3.1-flash-lite-preview
• gemini-3-pro-image-preview
• gemini-3-flash-preview
• veo-3.1-fast-generate-001
• veo-3.0-fast-generate-preview

Model → Pricing Page Mapping

Google – Gemini 3

Model ID	Publisher / Section	Source	Notes
gemini-3.1-pro-preview	Google – Gemini 3	API	$2/$12, cache $0.2, batch $1/$6, image_token $120/1M; web_search/enterprise $14/1000
gemini-3.1-flash-image-preview	Google – Gemini 3	API	$0.5/$3, batch $0.25/$1.5, image_token $60/1M
gemini-3.1-flash-lite-preview	Google – Gemini 3	API	$0.25/$1.5, cache $0.025, batch $0.125/$0.75
gemini-3-pro-preview	Google – Gemini 3	API	$2/$12, cache $0.2, batch $1/$6, image_token $120/1M
gemini-3-pro-image-preview	Google – Gemini 3	API	Matched to Gemini 3 Pro pricing (image variant); $2/$12, cache $0.2, batch $1/$6, image_token $120/1M
gemini-3-flash-preview	Google – Gemini 3	API	$0.5/$3, cache $0.05, batch $0.25/$1.5

Google – Gemini 2.5

Model ID	Publisher / Section	Source	Notes
gemini-2.5-pro	Google – Gemini 2.5	API	$1.25/$10, cache $0.125, batch $0.625/$5; web_search $35/1000, enterprise $45/1000
gemini-2.5-computer-use-preview-10-2025	Google – Gemini 2.5	API	Matched to Gemini 2.5 Pro Computer Use-Preview; $1.25/$10, no cache/batch listed
gemini-2.5-flash	Google – Gemini 2.5	API	$0.30/$2.50, cache $0.030, batch $0.15/$1.25, image_token $30/1M
gemini-2.5-flash-preview-09-2025	Google – Gemini 2.5	API	Preview alias → same pricing as gemini-2.5-flash
gemini-2.5-flash-lite	Google – Gemini 2.5	API	$0.10/$0.40, cache $0.010, batch $0.05/$0.20
gemini-2.5-flash-lite-preview-09-2025	Google – Gemini 2.5	API	Preview alias → same pricing as gemini-2.5-flash-lite
gemini-2.5-flash-image	Google – Gemini 2.5	API	Image output variant → same pricing as gemini-2.5-flash
gemini-2.5-flash-image-preview	Google – Gemini 2.5	API	Image output preview → same pricing as gemini-2.5-flash

Google – Gemini 2.0

Model ID	Publisher / Section	Source	Notes
gemini-2.0-flash-001	Google – Gemini 2.0	API	$0.15/$0.60, batch $0.075/$0.30; web_search $35/1000, enterprise $45/1000
gemini-2.0-flash-lite-001	Google – Gemini 2.0	API	$0.075/$0.30, batch $0.0375/$0.15

Google – Embedding

Model ID	Publisher / Section	Source	Notes
gemini-embedding-001	Google – Embedding	API	$0.00015/1K tokens input; batch $0.00012/1K
gemini-embedding-2-preview	Google – MultiModal Embeddings	API	$0.2/1M text tokens; image $0.00012/image, video $0.00079/frame, audio $0.00016/sec
text-embedding-005	Google – Embedding	API	$0.000025/1K chars (mapped as $/1K tokens)
text-multilingual-embedding-002	Google – Embedding	API	$0.000025/1K chars (mapped as $/1K tokens)
text-embedding-large-exp-03-07	Google – Embedding	API	Experimental; shares text embedding pricing $0.000025/1K tokens
textembedding-gecko	Google – Embedding	API	Legacy; shares text embedding pricing $0.000025/1K tokens
multimodalembedding	Google – MultiModal Embeddings	API	Per-image $0.0001, video-plus $0.0020/sec, standard $0.0010/sec, essential $0.0005/sec

Google – Imagen

Model ID	Publisher / Section	Source	Notes
imagen-4.0-ultra-generate-001	Google – Imagen	API	$0.06/image; row matched via lookup_variant imagen-4.0-ultra-generate
imagen-4.0-ultra-generate-preview-06-06	Google – Imagen	API	Preview variant; same pricing as ultra $0.06/image
imagen-4.0-generate-001	Google – Imagen	API	$0.04/image; row matched via lookup_variant imagen-4.0-generate
imagen-4.0-generate-preview-06-06	Google – Imagen	API	Preview variant; same pricing $0.04/image
imagen-4.0-fast-generate-001	Google – Imagen	API	$0.02/image; row matched via lookup_variant imagen-4.0-fast-generate
imagen-4.0-fast-generate-preview-06-06	Google – Imagen	API	Preview variant; same pricing $0.02/image
imagen-3.0-generate-002	Google – Imagen	API	$0.04/image (Imagen 3); row matched via lookup_variant imagen-3.0-generate
imagen-3.0-capability-001	Google – Imagen	API	Capability model → uses equivalent Imagen 3 generate price $0.04/image
imagen-3.0-capability-002	Google – Imagen	API	Capability model → uses equivalent Imagen 3 generate price $0.04/image
imagen-product-recontext-preview-06-30	Google – Imagen	API	Product Recontext $0.12/image

Google – Veo

Model ID	Publisher / Section	Source	Notes
veo-3.1-generate-001	Google – Veo	API	$0.20/sec (720p/1080p); default 8s, 1 sample
veo-3.1-generate-preview	Google – Veo	API	Preview alias → same $0.20/sec
veo-3.1-fast-generate-001	Google – Veo	API	$0.10/sec
veo-3.1-fast-generate-preview	Google – Veo	API	Preview alias → same $0.10/sec
veo-3.0-generate-001	Google – Veo	API	$0.20/sec
veo-3.0-generate-preview	Google – Veo	API	Preview alias → same $0.20/sec
veo-3.0-fast-generate-001	Google – Veo	API	$0.10/sec
veo-3.0-fast-generate-preview	Google – Veo	API	Preview alias → same $0.10/sec
veo-2.0-generate-001	Google – Veo	API	$0.50/sec

Google – Excluded (non-generative / global excludes)

Model ID	Reason
lyria-002	lyria-* music generation — excluded by global rule
gemini-2.5-flash-*-live-* / Live API models	-live- streaming — excluded by global rule
shieldgemma2	guard/safety model
pretrained-ocr	OCR model
virtual-try-on-001	virtual-try-on product model — excluded by Google ref
imagegeneration	Legacy superseded by Imagen 3+ — excluded by Google ref
translate-llm, text-translation, t5gemma	Translation/non-generative inference
gemma, gemma2, gemma3, gemma3n, paligemma, codegemma, functiongemma, translategemma, embeddinggemma	self-deploy only — excluded
multimodalembedding variants	Traditional CV/NLP
chirp-2, chirp-3, medasr	Audio transcription
video-text-detection, video-speech-transcription	Non-generative ML
bert-*, t5-*, resnet50, vit-jax, f-vlm-jax	Non-generative ML
All imageclassification-*, imageobjectdetection-*, imagesegmentation-*	CV classification/detection
occupancy-analytics, vehicle-detector, ppe-detector, people-blur, product-recognizer, tag-recognizer, object-detector, face-detector, dito, jax-owl-vit-v2	Non-generative CV
timesfm, weathernext, weather-next-v2	Forecasting/non-generative
path-foundation, derm-foundation, txgemma, hear, medgemma, medsiglip	Medical/self-deploy
earth-ai-imagery-*	Experimental earth imagery — non-generative
content-moderation, language-v1-*	Moderation/NLP
imagetext, imagewatermarkdetector, image-segmentation-001	Non-generative or detection
pretrained-form-parser, label-detector-pali-001, tab-net, text-detector, bart-large-cnn, vit-jax, pic2word, cloudnerf-pytorch-zipnerf, derm-foundation, cxr-foundation, mammut	Self-deploy or non-generative
pt-test, automl-*, tfvision-*, keras-yolov8	Internal/AutoML/CV

Anthropic – Claude

Model ID	Publisher / Section	Source	Notes
claude-opus-4-6	Anthropic – Claude	API	Stripped @default; $5/$25, cache_write $6.25 (5m), cache_read $0.50, batch $2.50/$12.50
claude-sonnet-4-6	Anthropic – Claude	API	Stripped @default; $3/$15, cache_write $3.75, cache_read $0.30, batch $1.50/$7.50
claude-opus-4-5@20251101	Anthropic – Claude	API	$5/$25, cache_write $6.25, cache_read $0.50, batch $2.50/$12.50
claude-sonnet-4-5@20250929	Anthropic – Claude	API	$3/$15, cache_write $3.75, cache_read $0.30, batch $1.50/$7.50
claude-haiku-4-5@20251001	Anthropic – Claude	API	$1/$5, cache_write $1.25, cache_read $0.10, batch $0.50/$2.50
claude-opus-4-1@20250805	Anthropic – Claude	API	Uniform pricing; $15/$75, cache_write $18.75, cache_read $1.50, batch $7.50/$37.50
claude-opus-4@20250514	Anthropic – Claude	API	Uniform pricing; $15/$75, cache_write $18.75, cache_read $1.50, batch $7.50/$37.50
claude-sonnet-4@20250514	Anthropic – Claude	API	Uniform pricing; $3/$15, cache_write $3.75, cache_read $0.30, batch $1.50/$7.50

OpenAI

Model ID	Publisher / Section	Source	Notes
gpt-oss-120b-maas	OpenAI	API	Matched to gpt-oss-120b on page; $0.09/$0.36, batch $0.045/$0.18
clip-vit-base-patch32	OpenAI	API – excluded	Self-deploy + non-generative embedding
openclip	OpenAI	API – excluded	Non-generative embedding
whisper-large	OpenAI	API – excluded	Audio transcription — excluded by global rule
gpt-oss	OpenAI	API – excluded	Self-deploy only

Meta – Llama

Model ID	Publisher / Section	Source	Notes
llama-3.3-70b-instruct-maas	Meta – Llama	API	Matched to Llama 3.3 70B; $0.72/$0.72, batch $0.36/$0.36
llama-4-maverick-17b-128e-instruct-maas	Meta – Llama	API	Matched to Llama 4 Maverick; $0.35/$1.15, batch $0.175/$0.575
llama-guard	Meta – Llama	API – excluded	Guard model — excluded by global rule
prompt-guard	Meta – Llama	API – excluded	Guard model — excluded by global rule
sam3	Meta – Llama	API – excluded	SAM3 segmentation — non-generative CV
faster-r-cnn, retinanet, mask-r-cnn, segment-anything	Meta	API – excluded	Non-generative CV
xlm-roberta-large, roberta-large	Meta	API – excluded	Non-generative NLP, self-deploy
codellama-7b-hf, llama2, nllb, imagebind, llama-2-quantized, llama3, llama3_1, llama4, llama3-2, llama3-3	Meta	API – excluded	Self-deploy only

Mistral AI

Model ID	Publisher / Section	Source	Notes
mistral-small-2503	Mistral AI	API	Matched to Mistral Small 3.1 (25.03); $0.10/$0.30
mistral-medium-3	Mistral AI	API	$0.40/$2.00
codestral-2	Mistral AI	API	$0.30/$0.90
mistral-ocr-2505	Mistral AI	API – excluded	OCR model
codestral-2501-self-deploy	Mistral AI	API – excluded	Self-deploy
ministral-3	Mistral AI	API – excluded	Self-deploy
mistral-large-3	Mistral AI	API – excluded	Self-deploy
mistral	Mistral AI (mistral-ai)	API – excluded	Self-deploy
mixtral	Mistral AI (mistral-ai)	API – excluded	Self-deploy

DeepSeek

Model ID	Publisher / Section	Source	Notes
deepseek-r1-0528-maas	DeepSeek	API	Matched to DeepSeek-R1 (0528); $1.35/$5.40, batch $0.675/$2.70
deepseek-v3.1-maas	DeepSeek	API	Matched to DeepSeek-V3.1; $0.60/$1.70, cache $0.06, batch $0.30/$0.85
deepseek-v3.2-maas	DeepSeek	API	Matched to DeepSeek-V3.2; $0.56/$1.68, cache $0.056, batch $0.28/$0.84
deepseek-r1	DeepSeek	API – excluded	Self-deploy
deepseek-v3	DeepSeek	API – excluded	Self-deploy
deepseek-v3-1	DeepSeek	API – excluded	Self-deploy
deepseek-v3-2	DeepSeek	API – excluded	Self-deploy
deepseek-ocr	DeepSeek	API – excluded	OCR model
deepseek-ocr-2	DeepSeek	API – excluded	OCR model, self-deploy
deepseek-ocr-maas	DeepSeek	API – excluded	OCR model

Kimi / Moonshot

Model ID	Publisher / Section	Source	Notes
kimi-k2-thinking-maas	Moonshot – Kimi	API	Matched to Kimi-K2-Thinking; $0.60/$2.50, cache $0.06
kimi-k2	Moonshot	API – excluded	Self-deploy
kimi-k2-5	Moonshot	API – excluded	Self-deploy

MiniMax

Model ID	Publisher / Section	Source	Notes
minimax-m2-maas	MiniMax	API	Matched to MiniMax-M2; $0.30/$1.20, cache $0.03
minimax-m2	MiniMax	API – excluded	Self-deploy

ZAI / GLM

Model ID	Publisher / Section	Source	Notes
glm-4.7-maas	ZAI – GLM	API	Matched to GLM-4.7; $0.60/$2.20
glm-5-maas	ZAI – GLM	API	Matched to GLM-5; $1/$3.20, cache $0.10
glm-4.7	ZAI – GLM	API – excluded	Self-deploy
glm-5	ZAI – GLM	API – excluded	Self-deploy
glm-4.5	ZAI – GLM	API – excluded	Self-deploy
glm-ocr	ZAI – GLM	API – excluded	OCR model
glm-image	ZAI – GLM	API – excluded	Image generation excluded by global policy

AI21

Model ID	Publisher / Section	Source	Notes
jamba-large-1.6	AI21	API – excluded	Self-deploy only; no MaaS variant; no AI21 section on pricing page

---

Generated by Pricing Agent on 2026-03-12