Skip to content

chore(pricing): Update google pricing#723

Open
siddharthsambharia-portkey wants to merge 105 commits intomainfrom
pricing-update/google
Open

chore(pricing): Update google pricing#723
siddharthsambharia-portkey wants to merge 105 commits intomainfrom
pricing-update/google

Conversation

@siddharthsambharia-portkey
Copy link
Copy Markdown
Collaborator

@siddharthsambharia-portkey siddharthsambharia-portkey commented Apr 16, 2026

🔄 Pricing Update: google

📊 Summary (complete_diff mode)

Change Type Count
➕ Models added 2
🔄 Models updated (merged) 25

➕ New Models

  • gemini-embedding-2-lte-128k
  • gemini-embedding-2-gt-128k

🔄 Updated Models

  • gemini-2.5-pro-lte-128k
  • gemini-2.0-flash-lte-128k
  • gemini-2.0-flash-gt-128k
  • gemini-2.0-flash-001-lte-128k
  • gemini-2.0-flash-001-gt-128k
  • gemini-2.0-flash-lite-lte-128k
  • gemini-2.0-flash-lite-gt-128k
  • gemini-2.0-flash-lite-001-lte-128k
  • gemini-2.0-flash-lite-001-gt-128k
  • gemini-3.1-flash-lite-preview-lte-128k
  • gemini-3.1-flash-lite-preview-gt-128k
  • gemini-flash-lite-latest-lte-128k
  • gemini-flash-lite-latest-gt-128k
  • gemini-embedding-001-lte-128k
  • gemini-embedding-001-gt-128k
  • veo-2.0-generate-001-lte-128k
  • veo-2.0-generate-001-gt-128k
  • veo-3.0-generate-001-lte-128k
  • veo-3.0-generate-001-gt-128k
  • veo-3.0-fast-generate-001-lte-128k
  • veo-3.0-fast-generate-001-gt-128k
  • veo-3.1-generate-preview-lte-128k
  • veo-3.1-generate-preview-gt-128k
  • veo-3.1-fast-generate-preview-lte-128k
  • veo-3.1-fast-generate-preview-gt-128k

Model → pricing page mapping

Pricing source: https://cloud.google.com/vertex-ai/generative-ai/pricing
Model list source: get_gemini_models API (50 models, 29 included after filtering)

Excluded models (with reason)

  • gemini-2.5-flash-preview-tts, gemini-2.5-pro-preview-tts, gemini-3.1-flash-tts-preview → TTS (excluded by rule)
  • gemma-3-1b-it, gemma-3-4b-it, gemma-3-12b-it, gemma-3-27b-it, gemma-3n-e4b-it, gemma-3n-e2b-it, gemma-4-26b-a4b-it, gemma-4-31b-it → Gemma (excluded by rule)
  • nano-banana-pro-preview → contains "nano" (excluded by *nano* rule)
  • gemini-2.5-computer-use-preview-10-2025 → computer-use model (excluded by rule)
  • gemini-robotics-er-1.5-preview, gemini-robotics-er-1.6-preview → Robotics (excluded by rule)
  • lyria-3-clip-preview, lyria-3-pro-preview → not Gemini/Imagen/Veo/Embedding category
  • deep-research-max-preview-04-2026, deep-research-preview-04-2026, deep-research-pro-preview-12-2025 → not in include list
  • aqa → excluded by rule

Gemini 2.5 Models

Model ID Pricing page section Notes
gemini-2.5-pro-lte-128k Gemini 2.5 Pro, ≤200K tier input $1.25, output $10, cache_read $0.13; batch $0.625/$5; web_search 3.5¢
gemini-2.5-pro-gt-128k Gemini 2.5 Pro, >200K tier input $2.50, output $15, cache_read $0.25; batch $1.25/$7.5; web_search 3.5¢
gemini-2.5-flash-lte-128k Gemini 2.5 Flash, flat pricing input $0.30, output $2.50, cache_read $0.03; batch $0.15/$1.25; web_search 3.5¢
gemini-2.5-flash-gt-128k Gemini 2.5 Flash, flat pricing same as lte (no context tiers)
gemini-2.5-flash-lite-lte-128k Gemini 2.5 Flash Lite, flat pricing input $0.10, output $0.40, cache_read $0.01; batch $0.05/$0.20; web_search 3.5¢
gemini-2.5-flash-lite-gt-128k Gemini 2.5 Flash Lite, flat pricing same as lte (no context tiers)
gemini-2.5-flash-image-lte-128k Gemini 2.5 Flash Image, flat pricing input $0.30, text output $2.50, image_token $30; batch $0.15/$1.25; batch image $15/1M noted
gemini-2.5-flash-image-gt-128k Gemini 2.5 Flash Image, flat pricing same as lte (no context tiers)

Gemini 2.0 Models

Model ID Pricing page section Notes
gemini-2.0-flash-lte-128k Gemini 2.0 Flash, flat pricing input $0.15, output $0.60; batch $0.075/$0.30; web_search 3.5¢
gemini-2.0-flash-gt-128k Gemini 2.0 Flash, flat pricing same as lte (no context tiers)
gemini-2.0-flash-001-lte-128k Gemini 2.0 Flash (versioned alias) same pricing as gemini-2.0-flash
gemini-2.0-flash-001-gt-128k Gemini 2.0 Flash (versioned alias) same as lte
gemini-2.0-flash-lite-lte-128k Gemini 2.0 Flash Lite, flat pricing input $0.075, output $0.30; batch $0.0375/$0.15; web_search 3.5¢
gemini-2.0-flash-lite-gt-128k Gemini 2.0 Flash Lite, flat pricing same as lte (no context tiers)
gemini-2.0-flash-lite-001-lte-128k Gemini 2.0 Flash Lite (versioned alias) same pricing as gemini-2.0-flash-lite
gemini-2.0-flash-lite-001-gt-128k Gemini 2.0 Flash Lite (versioned alias) same as lte

Gemini 3.x Models

Model ID Pricing page section Notes
gemini-3.1-pro-preview-lte-128k Gemini 3.1 Pro Preview, ≤200K tier input $2, output $12, cache_read $0.2; batch $1/$6; web_search 1.4¢ ($14/1K)
gemini-3.1-pro-preview-gt-128k Gemini 3.1 Pro Preview, >200K tier input $4, output $18, cache_read $0.4; batch $2/$9; web_search 1.4¢
gemini-3.1-pro-preview-customtools-lte-128k Gemini 3.1 Pro Preview (custom tools variant) same pricing as gemini-3.1-pro-preview
gemini-3.1-pro-preview-customtools-gt-128k Gemini 3.1 Pro Preview, >200K tier same as 3.1-pro-preview gt
gemini-3.1-flash-lite-preview-lte-128k Gemini 3.1 Flash-Lite Preview, flat pricing input $0.25, output $1.50, cache_read $0.03; batch $0.13/$0.75; web_search 1.4¢
gemini-3.1-flash-lite-preview-gt-128k Gemini 3.1 Flash-Lite Preview, flat pricing same as lte (no context tiers)
gemini-3.1-flash-image-preview-lte-128k Gemini 3.1 Flash Image Preview, flat pricing input $0.50, text output $3, image_token $60; batch $0.25/$1.50; batch image $30/1M noted; web_search 1.4¢
gemini-3.1-flash-image-preview-gt-128k Gemini 3.1 Flash Image Preview, flat pricing same as lte (no context tiers)
gemini-3-pro-preview-lte-128k Gemini 3 Pro Preview, ≤200K tier input $2, output $12, cache_read $0.2; batch $1/$6; web_search 1.4¢ (same prices as 3.1 Pro)
gemini-3-pro-preview-gt-128k Gemini 3 Pro Preview, >200K tier input $4, output $18, cache_read $0.4; batch $2/$9
gemini-3-flash-preview-lte-128k Gemini 3 Flash Preview, flat pricing input $0.5, output $3, cache_read $0.05; batch $0.25/$1.5; web_search 1.4¢
gemini-3-flash-preview-gt-128k Gemini 3 Flash Preview, flat pricing same as lte (no context tiers)
gemini-3-pro-image-preview-lte-128k Gemini 3 Pro Image Preview, flat pricing input $2, text output $12, image_token $120; batch $1/$6; batch image $60/1M noted; web_search 1.4¢
gemini-3-pro-image-preview-gt-128k Gemini 3 Pro Image Preview, flat pricing same as lte (no context tiers)

*-latest Alias Resolution

Model ID Resolved to Pricing source
gemini-flash-latest-lte-128k gemini-3-flash-preview (newest Flash on pricing page) input $0.5, output $3, cache $0.05; batch $0.25/$1.5; web_search 1.4¢
gemini-flash-latest-gt-128k gemini-3-flash-preview same as lte
gemini-flash-lite-latest-lte-128k gemini-3.1-flash-lite-preview (newest Flash-Lite on pricing page) input $0.25, output $1.50, cache $0.03; batch $0.13/$0.75; web_search 1.4¢
gemini-flash-lite-latest-gt-128k gemini-3.1-flash-lite-preview same as lte
gemini-pro-latest-lte-128k gemini-3.1-pro-preview (newest Pro on pricing page) input $2, output $12, cache $0.2; batch $1/$6; web_search 1.4¢
gemini-pro-latest-gt-128k gemini-3.1-pro-preview, >200K tier input $4, output $18, cache $0.4; batch $2/$9

Embedding Models

Model ID Pricing page section Notes
gemini-embedding-001-lte-128k Embeddings for Text (excl. Gemini Embedding), online $0.000025/1K chars ≈ $0.10/1M tokens; batch ≈ $0.08/1M tokens
gemini-embedding-001-gt-128k Embeddings for Text, flat pricing same as lte
gemini-embedding-2-lte-128k Gemini Embedding (standard), online $0.00015/1K tokens = $0.15/1M; batch $0.12/1M
gemini-embedding-2-gt-128k Gemini Embedding, flat pricing same as lte
gemini-embedding-2-preview-lte-128k Gemini Embedding 2 Unified Multimodal Preview text input $0.2/1M; image $0.00012/image; video $0.00079/frame; audio $0.00016/sec (image/video/audio priced separately, not captured in token fields)
gemini-embedding-2-preview-gt-128k Gemini Embedding 2 Unified Multimodal Preview same as lte

Imagen Models

Model ID Pricing page section Notes
imagen-4.0-generate-001-lte-128k Imagen 4 (standard generation) $0.04/image
imagen-4.0-generate-001-gt-128k Imagen 4, flat pricing same as lte
imagen-4.0-ultra-generate-001-lte-128k Imagen 4 Ultra $0.06/image
imagen-4.0-ultra-generate-001-gt-128k Imagen 4 Ultra, flat pricing same as lte
imagen-4.0-fast-generate-001-lte-128k Imagen 4 Fast $0.02/image
imagen-4.0-fast-generate-001-gt-128k Imagen 4 Fast, flat pricing same as lte

Veo Models

Model ID Pricing page section Notes
veo-2.0-generate-001-lte-128k Veo 2 $0.50/sec = 50¢/sec; default 8s, 1 sample
veo-2.0-generate-001-gt-128k Veo 2, flat pricing same as lte
veo-3.0-generate-001-lte-128k Veo 3 (video only, 720p/1080p) $0.20/sec = 20¢/sec; default 8s, 1 sample
veo-3.0-generate-001-gt-128k Veo 3, flat pricing same as lte
veo-3.0-fast-generate-001-lte-128k Veo 3 Fast (video only, 720p baseline) $0.08/sec = 8¢/sec; default 8s, 1 sample
veo-3.0-fast-generate-001-gt-128k Veo 3 Fast, flat pricing same as lte
veo-3.1-generate-preview-lte-128k Veo 3.1 (video only, 720p/1080p) $0.20/sec = 20¢/sec; default 8s, 1 sample
veo-3.1-generate-preview-gt-128k Veo 3.1, flat pricing same as lte
veo-3.1-fast-generate-preview-lte-128k Veo 3.1 Fast (video only, 720p baseline) $0.08/sec = 8¢/sec; default 8s, 1 sample
veo-3.1-fast-generate-preview-gt-128k Veo 3.1 Fast, flat pricing same as lte

Web Search Pricing Notes

  • Gemini 3.x models: $14 per 1,000 search queries = 1.4¢/query (includes 5,000 free queries/month)
  • Gemini 2.0/2.5 models: $35 per 1,000 grounded prompts = 3.5¢/prompt
  • Both web_search and search keys always set to the same value per skill requirements

Thinking Token Notes

  • No models have thinking tokens as a separate line item on the pricing page
  • All models show "text output (response and reasoning)" — reasoning/thinking is included in the output price
  • Therefore thinking_token additional field is not added to any model

Context Tier Mapping

  • Gemini 2.5 Pro and Gemini 3.x Pro models: ≤200K vs >200K tiers → mapped to lte-128k/gt-128k entries respectively
  • All other models (Flash, Lite, Image, Embedding, Imagen, Veo): flat pricing → lte-128k and gt-128k entries are identical

Generated by Pricing Agent on 2026-04-27

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant