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)	28

🔄 Updated Models

• gemini-2.5-pro
• gemini-2.5-flash
• gemini-2.5-flash-lite
• gemini-2.5-flash-preview-09-2025
• gemini-2.5-flash-lite-preview-09-2025
• gemini-2.0-flash-001
• gemini-3-pro-preview
• gemini-3-pro-image-preview
• gemini-3-flash-preview
• gemini-3.1-pro-preview
• gemini-3.1-flash-image-preview
• gemini-3.1-flash-lite-preview
• veo-3.1-generate-001
• veo-3.1-generate-preview
• veo-3.1-fast-generate-preview
• veo-3.0-generate-001
• veo-3.0-fast-generate-001
• veo-3.0-generate-preview
• veo-3.0-fast-generate-preview
• gemini-embedding-2-preview
• multimodalembedding
• gpt-oss-120b-maas
• qwen3-235b-a22b-instruct-2507-maas
• qwen3-next-80b-a3b-instruct-maas
• qwen3-next-80b-a3b-thinking-maas
• deepseek-r1-0528-maas
• deepseek-v3.1-maas
• deepseek-v3.2-maas

Model → Pricing Page Mapping

Google – Gemini (text/multimodal)

Model ID	Publisher / Section	Source	Notes
gemini-2.5-pro	Google – Gemini 2.5	API	Standard: $1.25/$10, cache_write $0.25, cache_read $0.13, batch $0.625/$5, web_search $35/1k, enterprise $45/1k
gemini-2.5-flash	Google – Gemini 2.5	API	Standard: $0.30/$2.50, cache_write $0.03, cache_read $0.03, batch $0.15/$1.25, image_token $30/1M
gemini-2.5-flash-lite	Google – Gemini 2.5	API	Standard: $0.10/$0.40, cache_write $0.01, cache_read $0.01, batch $0.05/$0.20
gemini-2.5-flash-preview-09-2025	Google – Gemini 2.5	API	Row matched via strip -preview-09-2025 → gemini-2.5-flash; same pricing
gemini-2.5-flash-lite-preview-09-2025	Google – Gemini 2.5	API	Row matched via strip -preview-09-2025 → gemini-2.5-flash-lite; same pricing
gemini-2.5-flash-image	Google – Gemini 2.5	API	Image output model: $0.30/$2.50, image_token $30/1M, batch $0.15/$1.25
gemini-2.5-computer-use-preview-10-2025	Google – Gemini 2.5	API – price not found	No pricing row found on page; added with price 0
gemini-2.0-flash-001	Google – Gemini 2.0	API	Standard: $0.15/$0.60, batch $0.075/$0.30, image_token $30/1M, web_search $35/1k
gemini-2.0-flash-lite-001	Google – Gemini 2.0	API	Standard: $0.075/$0.30, batch $0.0375/$0.15
gemini-3-pro-preview	Google – Gemini 3.0	API	$2/$12, cache $0.36/$0.20, batch $1/$1, image_token $120/1M, web_search $14/1k
gemini-3-pro-image-preview	Google – Gemini 3.0	API	Same row as Gemini 3 Pro (image variant)
gemini-3-flash-preview	Google – Gemini 3.0	API	$0.50/$3, cache $0.09/$0.05, batch $0.25/$1.5, image_token $60/1M
gemini-3.1-pro-preview	Google – Gemini 3.1	API	$2/$12, cache $0.36/$0.20, batch $1/$6, image_token $120/1M, web_search $14/1k
gemini-3.1-flash-image-preview	Google – Gemini 3.1	API	$0.50/$3, cache $0.09/$0.05, batch $0.25/$1.5, image_token $60/1M
gemini-3.1-flash-lite-preview	Google – Gemini 3.1	API	$0.25/$1.5, cache $0.05/$0.03, batch $0.13/$0.75, web_search $14/1k

Google – Imagen

Model ID	Publisher / Section	Source	Notes
imagen-4.0-ultra-generate-001	Google – Imagen 4 Ultra	API	Row matched via lookup_variant imagen-4.0-ultra-generate; $0.06/image
imagen-4.0-generate-001	Google – Imagen 4	API	Row matched via lookup_variant imagen-4.0-generate; $0.04/image
imagen-4.0-fast-generate-001	Google – Imagen 4 Fast	API	Row matched via lookup_variant imagen-4.0-fast-generate; $0.02/image
imagen-3.0-generate-002	Google – Imagen 3	API	Row matched via lookup_variant imagen-3.0-generate; $0.04/image
imagen-3.0-capability-001	Google – Imagen 3	API	Capability model → uses equivalent imagen-3.0-generate pricing; $0.04/image
imagen-3.0-capability-002	Google – Imagen 3	API	Capability model → uses equivalent imagen-3.0-generate pricing; $0.04/image

Google – Veo

Model ID	Publisher / Section	Source	Notes
veo-3.1-generate-001	Google – Veo 3.1	API	$0.40/sec, default 8s/1 sample
veo-3.1-fast-generate-001	Google – Veo 3.1 Fast	API	$0.15/sec, default 8s/1 sample
veo-3.1-generate-preview	Google – Veo 3.1	API	Preview alias → same pricing as veo-3.1-generate
veo-3.1-fast-generate-preview	Google – Veo 3.1 Fast	API	Preview alias → same pricing
veo-3.0-generate-001	Google – Veo 3.0	API	$0.40/sec; same rate as Veo 3.1
veo-3.0-fast-generate-001	Google – Veo 3.0 Fast	API	$0.15/sec
veo-3.0-generate-preview	Google – Veo 3.0	API	Preview alias → same pricing
veo-3.0-fast-generate-preview	Google – Veo 3.0 Fast	API	Preview alias → same pricing
veo-2.0-generate-001	Google – Veo 2.0	API	$0.50/sec

Google – Embeddings

Model ID	Publisher / Section	Source	Notes
gemini-embedding-001	Google – Embedding	API	$0.00015/1K tokens
gemini-embedding-2-preview	Google – Embedding	API	No dedicated row; using Gemini Embedding 001 pricing as same family
text-embedding-005	Google – Embedding	API	$0.000025/1K tokens
text-multilingual-embedding-002	Google – Embedding	API	$0.000025/1K tokens
text-embedding-large-exp-03-07	Google – Embedding	API	Experimental; shares text-embedding-005 pricing $0.000025/1K
textembedding-gecko	Google – Embedding	API	Legacy; uses text-embedding pricing $0.000025/1K
multimodalembedding	Google – Embedding	API	Multimodal: per-image $0.00012, per-video $0.00016

Anthropic – Claude

Model ID	Publisher / Section	Source	Notes
claude-opus-4-6	Anthropic – Claude	API	Stripped @default; $5/$25, cache_write(5m) $6.25, cache_read $0.5, batch $2.5/$12.5
claude-sonnet-4-6	Anthropic – Claude	API	Stripped @default; $3/$15, cache_write(5m) $3.75, cache_read $0.3, batch $1.5/$7.5
claude-opus-4-5@20251101	Anthropic – Claude	API	Pinned version; $5/$25, cache_write(5m) $6.25, cache_read $0.5
claude-opus-4-1@20250805	Anthropic – Claude	API	Pinned version; $15/$75, cache_write(5m) $18.75, cache_read $1.5
claude-opus-4@20250514	Anthropic – Claude	API	Pinned version; $15/$75, cache_write(5m) $18.75, cache_read $1.5
claude-sonnet-4-5@20250929	Anthropic – Claude	API	Pinned version; $3/$15, cache_write(5m) $3.75, cache_read $0.3
claude-sonnet-4@20250514	Anthropic – Claude	API	Pinned version; $3/$15, cache_write(5m) $3.75, cache_read $0.3
claude-haiku-4-5@20251001	Anthropic – Claude	API	Pinned version; $1/$5, cache_write(5m) $1.25, cache_read $0.1

OpenAI

Model ID	Publisher / Section	Source	Notes
gpt-oss-120b-maas	OpenAI	API	gpt-oss-120b row; $0.09/$0.36, cache_read $0.007, batch $0.045/$0.18
clip-vit-base-patch32	OpenAI	API – excluded	Non-generative (vision embedding)
openclip	OpenAI	API – excluded	Non-generative
whisper-large	OpenAI	API – excluded	Audio transcription, not generative inference
gpt-oss	OpenAI	API – excluded	Self-deploy only (has_deploy:true, no -maas suffix)

Meta – Llama

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

AI21

Model ID	Publisher / Section	Source	Notes
jamba-large-1.6	AI21	API – excluded	Self-deploy only (has_deploy:true, no -maas suffix); no MaaS pricing row

Qwen

Model ID	Publisher / Section	Source	Notes
qwen3-235b-a22b-instruct-2507-maas	Qwen – Qwen3-235B	API	$0.22/$0.88, cache_read $0.11, batch $0.11/$0.44
qwen3-coder-480b-a35b-instruct-maas	Qwen – Qwen3-Coder-480B	API	$0.22/$1.80, cache_read $0.022, batch $0.11/$0.90
qwen3-next-80b-a3b-instruct-maas	Qwen – Qwen3-Next-80B	API	$0.15/$1.20, cache_read $0.15, batch $0.15/$1.20
qwen3-next-80b-a3b-thinking-maas	Qwen – Qwen3-Next-80B Thinking	API	$0.15/$1.20, cache_read $0.15, batch $0.15/$1.20
qwq	Qwen	API – excluded	Self-deploy only
qwen3	Qwen	API – excluded	Self-deploy only
qwen3-embedding	Qwen	API – excluded	Self-deploy only
qwen3-5	Qwen	API – excluded	Self-deploy only
qwen2	Qwen	API – excluded	Self-deploy only
qwen3-coder-next	Qwen	API – excluded	Self-deploy only
qwen3-coder	Qwen	API – excluded	Self-deploy only
qwen-image	Qwen	API – excluded	Explicit policy exclusion (image gen, not on Vertex AI pricing)
qwen3-next	Qwen	API – excluded	Self-deploy only
qwen3-vl	Qwen	API – excluded	Self-deploy only

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
mistral	Mistral	API – excluded	Self-deploy only (mistral-ai publisher)
mixtral	Mistral	API – excluded	Self-deploy only (mistral-ai publisher)
codestral-2501-self-deploy	Mistral	API – excluded	Self-deploy (name contains self-deploy)
mistral-ocr-2505	Mistral	API – excluded	OCR model
ministral-3	Mistral	API – excluded	Self-deploy only
mistral-large-3	Mistral	API – excluded	Self-deploy only

DeepSeek

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

Kimi / Moonshot

Model ID	Publisher / Section	Source	Notes
kimi-k2-thinking-maas	Kimi – Kimi-K2-Thinking	API	$0.60/$2.50, cache_read $0.06
kimi-k2-5	Kimi	API – excluded	Self-deploy only
kimi-k2	Kimi	API – excluded	Self-deploy only

MiniMax

Model ID	Publisher / Section	Source	Notes
minimax-m2-maas	MiniMax – MiniMax-M2	API	$0.30/$1.20, cache_read $0.03
minimax-m2	MiniMax	API – excluded	Self-deploy only

ZAI-org / GLM

Model ID	Publisher / Section	Source	Notes
glm-4.7-maas	ZAI-org – GLM-4.7	API	$0.60/$2.20
glm-5-maas	ZAI-org – GLM-5	API	$1.00/$3.20
glm-4.7	ZAI-org	API – excluded	Self-deploy only
glm-5	ZAI-org	API – excluded	Self-deploy only
glm-ocr	ZAI-org	API – excluded	OCR model
glm-4.5	ZAI-org	API – excluded	Self-deploy only
glm-image	ZAI-org	API – excluded	Explicit policy exclusion (image gen, not on Vertex AI pricing)

---

Generated by Pricing Agent on 2026-03-24