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)	9

🔄 Updated Models

• gemini-2.5-pro
• 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
• gemini-embedding-2-preview

Model → Pricing Page Mapping

Model ID	Publisher / Section	Source	Notes
gemini-2.5-pro	Google – Gemini 2.5	API	Standard input $1.25/output $10 (≤200K); tiered pricing above 200K
gemini-2.5-computer-use-preview-10-2025	Google – Gemini 2.5	API	Matches "Gemini 2.5 Pro Computer Use-Preview" row
gemini-2.5-flash	Google – Gemini 2.5	API	Input $0.30, output $2.50
gemini-2.5-flash-preview-09-2025	Google – Gemini 2.5	API	Preview alias; uses gemini-2.5-flash pricing
gemini-2.5-flash-image	Google – Gemini 2.5	API	Matches "Gemini 2.5 Flash Image"; image_token $30/1M
gemini-2.5-flash-lite	Google – Gemini 2.5	API	Input $0.10, output $0.40
gemini-2.5-flash-lite-preview-09-2025	Google – Gemini 2.5	API	Preview alias; uses gemini-2.5-flash-lite pricing
gemini-2.0-flash-001	Google – Gemini 2.0	API	Input $0.15, output $0.60
gemini-2.0-flash-lite-001	Google – Gemini 2.0	API	Input $0.075, output $0.30
gemini-3.1-pro-preview	Google – Gemini 3	API	Input $2, output $12 (≤200K)
gemini-3.1-flash-image-preview	Google – Gemini 3	API	Input $0.50, output $3; image_token $60/1M
gemini-3.1-flash-lite-preview	Google – Gemini 3	API	Input $0.25, output $1.50
gemini-3-pro-preview	Google – Gemini 3	API	Input $2, output $12 (≤200K)
gemini-3-pro-image-preview	Google – Gemini 3	API	Input $2, output $12; image_token $120/1M
gemini-3-flash-preview	Google – Gemini 3	API	Input $0.50, output $3
imagen-4.0-generate-001	Google – Imagen	API	$0.04/image; row matched via lookup_variant imagen-4.0-generate
imagen-4.0-fast-generate-001	Google – Imagen	API	$0.02/image; row matched via imagen-4.0-fast-generate
imagen-4.0-ultra-generate-001	Google – Imagen	API	$0.06/image; row matched via imagen-4.0-ultra-generate
imagen-3.0-generate-002	Google – Imagen	API	$0.04/image; row matched via imagen-3.0-generate
imagen-3.0-capability-001	Google – Imagen	API	$0.04/image; uses imagen-3.0-generate pricing (capability shares generate price)
imagen-3.0-capability-002	Google – Imagen	API	$0.04/image; uses imagen-3.0-generate pricing (capability shares generate price)
veo-3.1-generate-001	Google – Veo	API	$0.20/sec (720p/1080p video); row matched via veo-3.1-generate
veo-3.1-generate-preview	Google – Veo	API	$0.20/sec (720p/1080p video); preview alias for veo-3.1
veo-3.1-fast-generate-001	Google – Veo	API	$0.10/sec (720p/1080p video); row matched via veo-3.1-fast-generate
veo-3.1-fast-generate-preview	Google – Veo	API	$0.10/sec; preview alias for veo-3.1-fast
veo-3.0-generate-001	Google – Veo	API	$0.20/sec (720p/1080p); row matched via veo-3.0-generate
veo-3.0-generate-preview	Google – Veo	API	$0.20/sec; preview alias for veo-3.0
veo-3.0-fast-generate-001	Google – Veo	API	$0.10/sec; row matched via veo-3.0-fast-generate
veo-3.0-fast-generate-preview	Google – Veo	API	$0.10/sec; preview alias for veo-3.0-fast
veo-2.0-generate-001	Google – Veo	API	$0.50/sec; row matched via veo-2.0-generate
gemini-embedding-001	Google – Gemini Embedding	API	$0.00015/1K tokens online, $0.00012/1K batch
gemini-embedding-2-preview	Google – Gemini Embedding	API	Preview; uses Gemini Embedding pricing
text-embedding-005	Google – Text Embedding	API	$0.000025/1K chars (per_thousand_tokens unit)
text-multilingual-embedding-002	Google – Text Embedding	API	$0.000025/1K chars
text-embedding-large-exp-03-07	Google – Text Embedding	API	Experimental; uses text-embedding pricing $0.000025/1K chars
textembedding-gecko	Google – Text Embedding	API	Legacy; uses text-embedding pricing $0.000025/1K chars
multimodalembedding	Google – Multimodal Embedding	API	Per-image $0.0001, video-plus $0.0020/sec, standard $0.0010/sec, essential $0.0005/sec
claude-opus-4-6	Anthropic – Claude	API	@default stripped; input $5, output $25; 5m cache write $6.25, cache hit $0.50
claude-sonnet-4-6	Anthropic – Claude	API	@default stripped; input $3, output $15; cache write $3.75, cache hit $0.30
claude-opus-4@20250514	Anthropic – Claude	API	Input $15, output $75; cache write $18.75, cache hit $1.50
claude-sonnet-4@20250514	Anthropic – Claude	API	Input $3, output $15; cache write $3.75, cache hit $0.30
claude-opus-4-1@20250805	Anthropic – Claude	API	Input $15, output $75; cache write $18.75, cache hit $1.50
claude-sonnet-4-5@20250929	Anthropic – Claude	API	Input $3, output $15; cache write $3.75, cache hit $0.30
claude-haiku-4-5@20251001	Anthropic – Claude	API	Input $1, output $5; cache write $1.25, cache hit $0.10
claude-opus-4-5@20251101	Anthropic – Claude	API	Input $5, output $25; cache write $6.25, cache hit $0.50
gpt-oss-120b-maas	OpenAI	API	Matches "gpt-oss-120b" row; input $0.09, output $0.36
llama-3.3-70b-instruct-maas	Meta – Llama	API	Matches "Llama 3.3 70B"; input $0.72, output $0.72
llama-4-maverick-17b-128e-instruct-maas	Meta – Llama	API	Matches "Llama 4 Maverick"; input $0.35, output $1.15
mistral-small-2503	Mistral AI	API	Matches "Mistral Small 3.1 (25.03)"; input $0.10, output $0.30
mistral-medium-3	Mistral AI	API	Input $0.40, output $2.00
codestral-2	Mistral AI	API	Input $0.30, output $0.90
deepseek-r1-0528-maas	DeepSeek	API	Matches "DeepSeek-R1 (0528)"; input $1.35, output $5.40
deepseek-v3.1-maas	DeepSeek	API	Matches "DeepSeek-V3.1"; input $0.60, output $1.70; cache hit $0.06
deepseek-v3.2-maas	DeepSeek	API	Matches "DeepSeek-V3.2"; input $0.56, output $1.68; cache hit $0.056
qwen3-235b-a22b-instruct-2507-maas	Qwen	API	Matches "Qwen3-235B-A22B-Instruct-2507"; input $0.22, output $0.88
qwen3-coder-480b-a35b-instruct-maas	Qwen	API	Matches "Qwen3-Coder-480B-A35B-Instruct"; input $0.22, output $1.80; cache hit $0.022
qwen3-next-80b-a3b-instruct-maas	Qwen	API	Matches "Qwen3-Next-80B-Instruct"; input $0.15, output $1.20
qwen3-next-80b-a3b-thinking-maas	Qwen	API	Matches "Qwen3-Next-80B-Thinking"; input $0.15, output $1.20
kimi-k2-thinking-maas	Kimi / Moonshot	API	Matches "Kimi-K2-Thinking"; input $0.60, output $2.50; cache hit $0.06
minimax-m2-maas	MiniMax	API	Matches "MiniMax-M2"; input $0.30, output $1.20; cache hit $0.03
glm-4.7-maas	ZAI.org / GLM	API	Matches "GLM-4.7"; input $0.60, output $2.20
glm-5-maas	ZAI.org / GLM	API	Matches "GLM-5"; input $1.00, output $3.20; cache hit $0.10

Excluded Models

Model ID	Publisher	Reason
gemini-live-2.5-flash-native-audio	Google	Gemini Live streaming — excluded per global rules
lyria-002	Google	Music generation — excluded per global rules
imagegeneration	Google	Legacy, superseded by imagen-3.0+ — excluded per google.md
virtual-try-on-001	Google	Product-specific retail model — excluded per google.md
pretrained-ocr	Google	OCR — excluded per global rules
shieldgemma2	Google	Safety/guard model — excluded per global rules
t5gemma, paligemma, codegemma, gemma, gemma2, gemma3, gemma3n, functiongemma, translategemma, embeddinggemma, mammut, txgemma, medgemma, medsiglip, medasr, hear, path-foundation, derm-foundation, cxr-foundation, bert-base-uncased, timesfm, weathernext	Google	Self-deploy only or non-generative ML — excluded per google.md
chirp-2, chirp-3	Google	Audio transcription, not generative inference — excluded
translate-llm, text-translation	Google	Translation, not generative inference
video-text-detection, video-speech-transcription	Google	Non-generative CV/transcription
earth-ai-imagery-owlvit-eap-10-2025, earth-ai-imagery-mammut-eap-10-2025	Google	Non-generative vision models
image-segmentation-001	Google	Image segmentation — non-generative
Various legacy/CV models	Google	Non-generative: imageclassification-, imageobjectdetection-, bert-base, resnet50, etc.
clip-vit-base-patch32, openclip	OpenAI	Non-generative (vision embedding/classification)
whisper-large	OpenAI	Audio transcription — excluded per openai.md
gpt-oss	OpenAI	Self-deploy (has_deploy: true, no -maas suffix)
faster-r-cnn, retinanet, mask-r-cnn, segment-anything, sam3	Meta	Non-generative CV
roberta-large, xlm-roberta-large, nllb, imagebind	Meta	Non-generative NLP/embedding
llama-guard, prompt-guard	Meta	Safety/guard models
codellama-7b-hf, llama2, llama-2-quantized, llama3, llama3_1, llama3-2, llama3-3, llama4	Meta	Self-deploy only (has_deploy: true, no -maas)
mistral, mixtral	Mistral (mistral-ai)	Self-deploy only
codestral-2501-self-deploy	Mistral (mistralai)	Self-deploy (name contains self-deploy)
mistral-ocr-2505	Mistral	OCR — excluded per global rules
ministral-3, mistral-large-3	Mistral	Self-deploy only
deepseek-r1, deepseek-v3, deepseek-v3-1, deepseek-v3-2	DeepSeek	Self-deploy only
deepseek-ocr, deepseek-ocr-2, deepseek-ocr-maas	DeepSeek	OCR — excluded per global rules
qwq, qwen3, qwen3-embedding, qwen3-5, qwen2, qwen3-coder, qwen3-coder-next, qwen3-next, qwen3-vl	Qwen	Self-deploy only
qwen-image	Qwen	Excluded by policy (qwen-image)
kimi-k2, kimi-k2-5	Kimi	Self-deploy only
minimax-m2	MiniMax	Self-deploy only
glm-4.7, glm-5, glm-4.5	ZAI.org	Self-deploy only
glm-ocr	ZAI.org	OCR — excluded per global rules
glm-image	ZAI.org	Excluded by policy (glm-image)
jamba-large-1.6	AI21	Self-deploy only (has_deploy: true, no -maas)

---

Generated by Pricing Agent on 2026-03-24