chore(pricing): Update vertex-ai pricing

[siddharthsambharia-portkey]

🔄 Pricing Update: vertex-ai

📊 Summary (complete_diff mode)

Change Type	Count
➕ Models added	2
🔄 Models updated (merged)	23

➕ New Models

• gemini-2.5-pro-tts
• gemini-2.5-flash-tts

🔄 Updated Models

• gemini-2.5-pro
• gemini-2.5-flash
• gemini-2.5-flash-lite
• gemini-2.5-flash-image
• gemini-2.0-flash-001
• gemini-2.5-flash-preview-09-2025
• gemini-2.5-flash-lite-preview-09-2025
• gemini-3-pro-preview
• gemini-3-flash-preview
• gemini-3-pro-image-preview
• gemini-3.1-pro-preview
• gemini-3.1-flash-lite-preview
• gemini-3.1-flash-image-preview
• veo-3.1-fast-generate-001
• veo-3.0-fast-generate-preview
• gemini-embedding-001
• gemini-embedding-2-preview
• text-embedding-005
• text-multilingual-embedding-002
• text-embedding-large-exp-03-07
• multimodalembedding@001
• claude-opus-4-1@20250805
• claude-opus-4@20250514

Model → Pricing Page Mapping

Google – Gemini (token pricing, $/1M)

Model ID	Publisher / Section	Source	Notes
gemini-2.5-pro	Google – Gemini 2.5 Pro	API	input $1.25, output $10, cache_read $0.31, batch $0.625/$5, web_search 3.5¢, enterprise_web_search 4.5¢
gemini-2.5-flash	Google – Gemini 2.5 Flash	API	input $0.30, output $2.50, cache_read $0.075, batch $0.15/$1.25, web_search 3.5¢, enterprise_web_search 4.5¢
gemini-2.5-flash-lite	Google – Gemini 2.5 Flash Lite	API	input $0.10, output $0.40, cache_read $0.025, batch $0.05/$0.20, web_search 3.5¢, enterprise_web_search 4.5¢
gemini-2.5-flash-image	Google – Gemini 2.5 Flash (image variant)	API	Same token pricing as gemini-2.5-flash + image_token $30/1M
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-2.0-flash-001	Google – Gemini 2.0 Flash	API	input $0.15, output $0.60, cache_read $0.0375, batch $0.075/$0.30, web_search 3.5¢
gemini-2.0-flash-lite-001	Google – Gemini 2.0 Flash Lite	API	input $0.075, output $0.30, web_search 3.5¢
gemini-3-pro-preview	Google – Gemini 3 Pro	API	input $2.00, output $12.00, batch $1/$6, web_search 1.4¢, enterprise_web_search 4.5¢
gemini-3-flash-preview	Google – Gemini 3 Flash	API	input $0.50, output $3.00, batch $0.25/$1.50, web_search 1.4¢, enterprise_web_search 4.5¢
gemini-3-pro-image-preview	Google – Gemini 3 Pro (image variant)	API	Same as gemini-3-pro-preview + image_token $120/1M
gemini-3.1-pro-preview	Google – Gemini 3.1 Pro	API	input $2.00, output $12.00, batch $1/$6, web_search 1.4¢, enterprise_web_search 4.5¢
gemini-3.1-flash-lite-preview	Google – Gemini 3.1 Flash Lite	API	input $0.25, output $1.50, batch $0.125/$0.75, web_search 1.4¢, enterprise_web_search 4.5¢
gemini-3.1-flash-image-preview	Google – Gemini 3.1 Flash (image variant)	API	input $0.25, output $1.50 + image_token $60/1M, web_search 1.4¢
gemini-2.5-computer-use-preview-10-2025	Google – Gemini 2.5 (computer use)	API – price not found	No dedicated pricing row; added with price 0
gemini-2.5-pro-tts	Google – Gemini 2.5 TTS	API – price not found	TTS model excluded from generative AI pricing page
gemini-2.5-flash-tts	Google – Gemini 2.5 TTS	API – price not found	TTS model excluded from generative AI pricing page

Google – Imagen (per-image pricing)

Model ID	Publisher / Section	Source	Notes
imagen-4.0-ultra-generate-001	Google – Imagen 4.0 Ultra	API	$0.06/image
imagen-4.0-generate-001	Google – Imagen 4.0	API	$0.04/image
imagen-4.0-fast-generate-001	Google – Imagen 4.0 Fast	API	$0.02/image
imagen-3.0-generate-002	Google – Imagen 3.0	API	$0.04/image
imagen-3.0-capability-001	Google – Imagen 3.0 (capability)	API	Priced same as imagen-3.0-generate per schema rules ($0.04/image)
imagen-3.0-capability-002	Google – Imagen 3.0 (capability)	API	Priced same as imagen-3.0-generate per schema rules ($0.04/image)

Google – Veo (per-second video pricing)

Model ID	Publisher / Section	Source	Notes
veo-3.1-generate-001	Google – Veo 3.1	API	$0.20/sec video, 8s default, 1 sample
veo-3.1-fast-generate-001	Google – Veo 3.1 Fast	API	$0.10/sec video, 8s default, 1 sample
veo-3.1-generate-preview	Google – Veo 3.1	API	Preview alias — priced same as veo-3.1-generate-001
veo-3.1-fast-generate-preview	Google – Veo 3.1 Fast	API	Preview alias — priced same as veo-3.1-fast-generate-001
veo-3.0-generate-001	Google – Veo 3.0	API	$0.20/sec video, 8s default, 1 sample
veo-3.0-fast-generate-001	Google – Veo 3.0 Fast	API	$0.10/sec video, 8s default, 1 sample
veo-3.0-generate-preview	Google – Veo 3.0	API	Preview alias — priced same as veo-3.0-generate-001
veo-3.0-fast-generate-preview	Google – Veo 3.0 Fast	API	Preview alias — priced same as veo-3.0-fast-generate-001
veo-2.0-generate-001	Google – Veo 2.0	API	$0.50/sec video, 8s default, 1 sample

Google – Embedding

Model ID	Publisher / Section	Source	Notes
gemini-embedding-001	Google – Gemini Embedding	API	$0.00015/1K tokens
gemini-embedding-2-preview	Google – Gemini Embedding	API	Preview; priced same as gemini-embedding-001
text-embedding-005	Google – Text Embedding	API	$0.000025/1K characters (per_million_characters unit)
text-multilingual-embedding-002	Google – Text Multilingual Embedding	API	$0.000025/1K characters
text-embedding-large-exp-03-07	Google – Text Embedding Large (experimental)	API	Priced same as gemini-embedding family ($0.00015/1K tokens)
textembedding-gecko@003	Google – Legacy Embedding	API – price not found	Legacy model; no dedicated pricing row
textembedding-gecko-multilingual@001	Google – Legacy Embedding	API – price not found	Legacy model; no dedicated pricing row
multimodalembedding@001	Google – Multimodal Embedding	API	Per-image $0.002¢, per-video-standard $0.002¢

Anthropic – Claude

Model ID	Publisher / Section	Source	Notes
claude-opus-4-6	Anthropic – Claude Opus 4.6	API	@default stripped; $5/$25, cache_write $6.25, cache_read $0.50
claude-sonnet-4-6	Anthropic – Claude Sonnet 4.6	API	@default stripped; $3/$15, cache_write $3.75, cache_read $0.30
claude-opus-4-5@20251101	Anthropic – Claude Opus 4.5	API	Pinned version; $5/$25, cache_write $6.25, cache_read $0.50
claude-sonnet-4-5@20250929	Anthropic – Claude Sonnet 4.5	API	Pinned version; $3/$15, cache_write $3.75, cache_read $0.30
claude-haiku-4-5@20251001	Anthropic – Claude Haiku 4.5	API	Pinned version; $1/$5, cache_write $1.25, cache_read $0.10
claude-opus-4-1@20250805	Anthropic – Claude Opus 4.1	API	Pinned version; $5/$25, cache_write $6.25, cache_read $0.50
claude-opus-4@20250514	Anthropic – Claude Opus 4	API	Pinned version; $5/$25, cache_write $6.25, cache_read $0.50
claude-sonnet-4@20250514	Anthropic – Claude Sonnet 4	API	Pinned version; $3/$15, cache_write $3.75, cache_read $0.30

OpenAI – GPT

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

OpenAI models excluded (self-deploy / whisper): gpt-4o-self-deploy, gpt-4o-mini-self-deploy, o3-self-deploy, o4-mini-self-deploy, whisper-1

Meta – Llama

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

Meta models excluded: llama-guard-*, prompt-guard-* (guard models); faster-rcnn-*, retinanet-*, mask-rcnn-*, segment-anything-*, sam3-* (non-generative CV); xlm-roberta-*, roberta-* (non-generative NLP); nllb-* (translation); imagebind-* (non-generative); all self-deploy without -maas suffix

Qwen

Model ID	Publisher / Section	Source	Notes
qwen3-235b-a22b-instruct-2507-maas	Qwen – Qwen3 235B	API	$0.22/$0.88
qwen3-coder-480b-a35b-instruct-maas	Qwen – Qwen3 Coder 480B	API	$0.22/$1.80
qwen3-next-80b-a3b-instruct-maas	Qwen – Qwen3 Next 80B	API	$0.15/$1.20
qwen3-next-80b-a3b-thinking-maas	Qwen – Qwen3 Next 80B (thinking)	API	$0.15/$1.20 (same row as instruct)

Qwen excluded: qwen-image (explicit policy); all self-deploy models without -maas suffix

Mistral

Model ID	Publisher / Section	Source	Notes
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 2	API	$0.30/$0.90

Mistral excluded: mistral-ocr-2505 (OCR); codestral-2501-self-deploy, ministral-3, mistral-large-3 (self-deploy without -maas); mistral/mixtral from mistral-ai namespace (self-deploy)

DeepSeek

Model ID	Publisher / Section	Source	Notes
deepseek-r1-0528-maas	DeepSeek – DeepSeek R1 0528	API	$1.35/$5.40
deepseek-v3.1-maas	DeepSeek – DeepSeek V3.1	API	$0.60/$1.70
deepseek-v3.2-maas	DeepSeek – DeepSeek V3.2	API	$0.56/$1.68

DeepSeek excluded: deepseek-ocr-maas (OCR by name); all self-deploy variants (deepseek-r1, deepseek-v3, etc. without -maas)

Kimi / Moonshot

Model ID	Publisher / Section	Source	Notes
kimi-k2-thinking-maas	Moonshot – Kimi K2 Thinking	API	$0.60/$2.50

Kimi excluded: kimi-k2, kimi-k2-5 (self-deploy without -maas)

MiniMax

Model ID	Publisher / Section	Source	Notes
minimax-m2-maas	MiniMax – MiniMax M2	API	$0.30/$1.20

MiniMax excluded: minimax-m2 (self-deploy without -maas)

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

ZAI excluded: glm-image (explicit policy); glm-ocr (OCR); glm-4.7, glm-5, glm-4.5 (self-deploy without -maas)

AI21

AI21: jamba-large-1.6 — self-deploy (has_deploy: true, no -maas suffix); excluded per partner rules. No includable models from AI21.

---

Generated by Pricing Agent on 2026-04-01