chore(pricing): Update vertex-ai pricing

[siddharthsambharia-portkey]

🔄 Pricing Update: vertex-ai

📊 Summary (complete_diff mode)

Change Type	Count
➕ Models added	8
🔄 Models updated (merged)	27

➕ New Models

• llama3
• llama3_1
• llama3-2
• llama3-3
• llama4
• llama2
• llama-2-quantized
• codellama-7b-hf

🔄 Updated Models

• gemini-2.5-pro
• gemini-2.5-computer-use-preview-10-2025
• 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
• gemini-embedding-2-preview
• multimodalembedding
• veo-2.0-generate-001
• veo-3.0-generate-001
• veo-3.0-fast-generate-001
• veo-3.0-generate-preview
• veo-3.0-fast-generate-preview
• veo-3.1-generate-001
• veo-3.1-fast-generate-001
• veo-3.1-generate-preview
• veo-3.1-fast-generate-preview
• claude-opus-4-6
• claude-sonnet-4-6
• claude-haiku-4-5@20251001
• deepseek-r1-0528-maas
• deepseek-v3.1-maas
• deepseek-v3.2-maas
• qwen3-coder-480b-a35b-instruct-maas
• qwen3-next-80b-a3b-instruct-maas
• qwen3-next-80b-a3b-thinking-maas

Model-to-Pricing-Page Mapping

Model ID	Publisher / Section	Source	Notes
gemini-2.5-pro	Google – Gemini 2.5	API	Standard: $1.25/$10, 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_read $0.03, batch $0.15/$1.25, web_search $35/1k, enterprise $45/1k
gemini-2.5-flash-lite	Google – Gemini 2.5	API	Standard: $0.10/$0.40, cache_read $0.01, batch $0.05/$0.20, web_search $35/1k, enterprise $45/1k
gemini-2.5-flash-image	Google – Gemini 2.5	API	$0.30/$2.50, image_token $30/1M, batch $0.15/$1.25, web_search $35/1k
gemini-2.5-flash-preview-09-2025	Google – Gemini 2.5	API	Preview alias for gemini-2.5-flash; same pricing
gemini-2.5-flash-lite-preview-09-2025	Google – Gemini 2.5	API	Preview alias for gemini-2.5-flash-lite; same pricing
gemini-2.5-computer-use-preview-10-2025	Google – Gemini 2.5	API	Same pricing as gemini-2.5-pro
gemini-2.0-flash-001	Google – Gemini 2.0	API	$0.15/$0.60, batch $0.075/$0.30, no cache, web_search $35/1k, enterprise $45/1k
gemini-2.0-flash-lite-001	Google – Gemini 2.0	API	$0.075/$0.30, batch $0.0375/$0.15, no cache, web_search $35/1k, enterprise $45/1k
gemini-3-pro-preview	Google – Gemini 3	API	$2/$12, cache_read $0.20, batch $1/$6, image_token $120/1M, web_search $14/1k, enterprise $14/1k
gemini-3-pro-image-preview	Google – Gemini 3	API	Same as gemini-3-pro-preview pricing
gemini-3-flash-preview	Google – Gemini 3	API	$0.50/$3, cache_read $0.05, batch $0.25/$1.50, web_search $14/1k, enterprise $14/1k
gemini-3.1-pro-preview	Google – Gemini 3	API	$2/$12, cache_read $0.20, batch $1/$6, image_token $60/1M, web_search $14/1k, enterprise $14/1k
gemini-3.1-flash-image-preview	Google – Gemini 3	API	$0.50/$3, batch $0.25/$1.50, image_token $30/1M, web_search $14/1k, enterprise $14/1k
gemini-3.1-flash-lite-preview	Google – Gemini 3	API	$0.25/$1.50, cache_read $0.03, batch $0.13/$0.75, web_search $14/1k, enterprise $14/1k
gemini-embedding-001	Google – Embedding	API	$0.00015/1K tokens
gemini-embedding-2-preview	Google – Embedding	API	$0.00015/1K tokens (same as gemini-embedding-001)
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	$0.000025/1K tokens (same as text-embedding-005)
multimodalembedding	Google – Embedding	API	$0.0002/1K tokens, per-image $0.0001, per-video+ $0.0005
textembedding-gecko	Google – Embedding	API – price not found	Legacy model, no pricing row found; price 0
imagen-4.0-generate-001	Google – Imagen 4	API	$0.04/image; matched via lookup_variant imagen-4.0-generate
imagen-4.0-fast-generate-001	Google – Imagen 4	API	$0.02/image; matched via lookup_variant imagen-4.0-fast-generate
imagen-4.0-ultra-generate-001	Google – Imagen 4	API	$0.06/image; matched via lookup_variant imagen-4.0-ultra-generate
imagen-3.0-generate-002	Google – Imagen 3	API	$0.04/image; matched via lookup_variant imagen-3.0-generate
imagen-3.0-capability-001	Google – Imagen 3	API	Capability model; uses equivalent generate pricing $0.04/image
imagen-3.0-capability-002	Google – Imagen 3	API	Capability model; uses equivalent generate pricing $0.04/image
veo-2.0-generate-001	Google – Veo 2.0	API	50 cents/sec, duration 1, count 1
veo-3.0-generate-001	Google – Veo 3.0	API	40 cents/sec, duration 1, count 1
veo-3.0-fast-generate-001	Google – Veo 3.0 Fast	API	15 cents/sec, duration 1, count 1
veo-3.0-generate-preview	Google – Veo 3.0	API	Preview alias; same pricing as veo-3.0-generate-001
veo-3.0-fast-generate-preview	Google – Veo 3.0 Fast	API	Preview alias; same pricing as veo-3.0-fast-generate-001
veo-3.1-generate-001	Google – Veo 3.1	API	40 cents/sec, duration 1, count 1
veo-3.1-fast-generate-001	Google – Veo 3.1 Fast	API	35 cents/sec, duration 1, count 1
veo-3.1-generate-preview	Google – Veo 3.1	API	Preview alias; same pricing as veo-3.1-generate-001
veo-3.1-fast-generate-preview	Google – Veo 3.1 Fast	API	Preview alias; same pricing as veo-3.1-fast-generate-001
claude-opus-4-6	Anthropic – Claude	API	$5.50/$27.50, cache_write $6.875, cache_read $0.55, batch $2.75/$13.75; @default stripped
claude-sonnet-4-6	Anthropic – Claude	API	$3.30/$16.50, cache_write $4.13, cache_read $0.33, batch $1.65/$8.25; @default stripped
claude-sonnet-4-5@20250929	Anthropic – Claude	API	$3/$15, cache_write $3.75, cache_read $0.30, batch $1.50/$7.50
claude-sonnet-4@20250514	Anthropic – Claude	API	$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-opus-4-1@20250805	Anthropic – Claude	API	$15/$75, cache_write $18.75, cache_read $1.50, batch $7.50/$37.50
claude-opus-4@20250514	Anthropic – Claude	API	$15/$75, cache_write $18.75, cache_read $1.50, batch $7.50/$37.50
claude-haiku-4-5@20251001	Anthropic – Claude	API	$1.10/$5.50, cache_write $1.375, cache_read $0.11, batch $0.55/$2.75
llama-3.3-70b-instruct-maas	Meta – Llama	API	$0.72/$0.72, batch $0.36/$0.36
llama-4-maverick-17b-128e-instruct-maas	Meta – Llama 4	API	$0.35/$1.15, batch $0.175/$0.575
llama3	Meta – Llama	API – price not found	Self-deploy only (has_deploy: true, no -maas); price 0
llama3_1	Meta – Llama	API – price not found	Self-deploy only; price 0
llama3-2	Meta – Llama	API – price not found	Self-deploy only; price 0
llama3-3	Meta – Llama	API – price not found	Self-deploy only; price 0
llama4	Meta – Llama	API – price not found	Self-deploy only; price 0
llama2	Meta – Llama	API – price not found	Self-deploy only; price 0
llama-2-quantized	Meta – Llama	API – price not found	Self-deploy only; price 0
codellama-7b-hf	Meta – Llama	API – price not found	Self-deploy only; price 0
mistral-small-2503	Mistral – Mistral Small	API	$0.10/$0.30
mistral-medium-3	Mistral – Mistral Medium	API	$0.40/$2.00
codestral-2	Mistral – Codestral	API	$0.30/$0.90
gpt-oss-120b-maas	OpenAI – GPT OSS	API	$0.09/$0.36, batch $0.045/$0.18
deepseek-r1-0528-maas	DeepSeek – R1	API	$1.35/$5.40, cache_write $0.675, cache_read $0.06, batch $0.675/$2.70
deepseek-v3.1-maas	DeepSeek – V3.1	API	$0.60/$1.70, cache_write $0.30, cache_read $0.06, batch $0.30/$0.85
deepseek-v3.2-maas	DeepSeek – V3.2	API	$0.56/$1.68, cache_write $0.28, cache_read $0.056, batch $0.28/$0.84
qwen3-235b-a22b-instruct-2507-maas	Qwen – Qwen3-235B	API	$0.22/$0.88, batch $0.11/$0.44
qwen3-coder-480b-a35b-instruct-maas	Qwen – Qwen3-Coder-480B	API	$0.22/$1.80, cache_write $0.11, cache_read $0.022, batch $0.11/$0.90
qwen3-next-80b-a3b-instruct-maas	Qwen – Qwen3-Next-80B	API	$0.15/$1.20, batch $0.11/$0.90
qwen3-next-80b-a3b-thinking-maas	Qwen – Qwen3-Next-80B Thinking	API	$0.15/$1.20, batch $0.11/$0.90
kimi-k2-thinking-maas	MoonshotAI – Kimi K2	API	$0.60/$2.50
minimax-m2-maas	MiniMax – M2	API	$0.30/$1.20
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

Excluded models (not added to output)

Model ID	Publisher	Reason
gemini-live-2.5-flash-native-audio	Google	*-live-* streaming — excluded by global rule
lyria-002, lyria-3-pro-preview, lyria-3-clip-preview	Google	lyria-* music generation — excluded by global rule
imagegeneration	Google	Legacy model excluded by google.md rule
virtual-try-on-001	Google	Product-specific retail model excluded by google.md
pretrained-ocr	Google	OCR model — excluded by global rule
shieldgemma2	Google	Safety/guard model — excluded
gemma, gemma2, gemma3, gemma3n, functiongemma, paligemma, codegemma, translategemma, t5gemma, embeddinggemma	Google	Self-deploy Gemma variants — excluded
chirp-2, chirp-3	Google	Audio transcription/speech — excluded
translate-llm	Google	Non-generative translation — excluded
video-text-detection, video-speech-transcription	Google	Non-generative CV/NLP — excluded
text-translation	Google	Non-generative NLP — excluded
image-segmentation-001	Google	Non-generative CV — excluded
weathernext, weather-next-v2	Google	Non-generative forecasting — excluded
timesfm	Google	Time-series forecasting (self-deploy) — excluded
bert-base, bert-base-uncased, t5-flan, t5-1.1	Google	Non-generative NLP self-deploy — excluded
imageclassification-*, imageobjectdetection-*, imagesegmentation-*	Google	Non-generative CV — excluded
earth-ai-imagery-*	Google	Non-generative vision — excluded
path-foundation, derm-foundation, txgemma, hear, medgemma, medsiglip, medasr, cxr-foundation	Google	Medical/specialized self-deploy — non-generative for pricing purposes
mammut, jax-owl-vit-v2, dito, cloudnerf-pytorch-zipnerf, owlvit-base-patch32, vit-jax, pic2word, f-vlm-jax, keras-yolov8, tab-net, tfvision-*, automl-*, resnet50, bart-large-cnn	Google	Non-generative ML / self-deploy only — excluded
label-detector-pali-001, content-moderation, imagewatermarkdetector, imagetext, language-v1-*	Google	Non-generative or legacy — excluded
pt-test, occupancy-analytics, vehicle-detector, object-detector, ppe-detector, people-blur, product-recognizer, tag-recognizer	Google	Non-generative specialized models — excluded
face-detector, pretrained-form-parser, text-detector, imagebind	Google/Meta	Non-generative — excluded
llama-guard, prompt-guard	Meta	Guard/safety models — excluded by global rule
faster-r-cnn, retinanet, mask-r-cnn, segment-anything, sam3	Meta	Non-generative CV — excluded
xlm-roberta-large, roberta-large, nllb	Meta	Non-generative NLP — excluded
mistral, mixtral	Mistral (mistral-ai)	Self-deploy only (has_deploy: true, no -maas) — excluded
codestral-2501-self-deploy	Mistral	Self-deploy model (name contains self-deploy) — excluded
ministral-3, mistral-large-3	Mistral	Self-deploy (has_deploy: true, no -maas) — excluded
mistral-ocr-2505	Mistral	OCR model — excluded by global rule
clip-vit-base-patch32, openclip	OpenAI	Non-generative embedding — excluded
whisper-large	OpenAI	Audio transcription — excluded
gpt-oss	OpenAI	Self-deploy (has_deploy: true, no -maas) — excluded
deepseek-r1, deepseek-v3, deepseek-v3-1, deepseek-v3-2	DeepSeek	Self-deploy (has_deploy: true, no -maas) — excluded
deepseek-ocr, deepseek-ocr-2, deepseek-ocr-maas	DeepSeek	OCR models — excluded by global rule
qwq, qwen3, qwen3-5, qwen2, qwen3-coder, qwen3-coder-next, qwen3-next, qwen3-vl	Qwen	Self-deploy (has_deploy: true, no -maas) — excluded
qwen3-embedding	Qwen	Self-deploy embedding — excluded
qwen-image	Qwen	Excluded by explicit policy (qwen-image)
jamba-large-1.6	AI21	Self-deploy only (has_deploy: true, no -maas) — excluded
kimi-k2-5, kimi-k2	MoonshotAI	Self-deploy (has_deploy: true, no -maas) — excluded
minimax-m2	MiniMax	Self-deploy (has_deploy: true, no -maas) — excluded
glm-4.7, glm-5, glm-4.5	ZAI.org	Self-deploy (has_deploy: true, no -maas) — excluded
glm-ocr	ZAI.org	OCR model — excluded by global rule
glm-image	ZAI.org	Excluded by explicit policy (glm-image)

---

Generated by Pricing Agent on 2026-03-26