Skip to content

chore(pricing): Update google pricing#648

Open
siddharthsambharia-portkey wants to merge 2 commits intomainfrom
pricing-update/google-24257386432
Open

chore(pricing): Update google pricing#648
siddharthsambharia-portkey wants to merge 2 commits intomainfrom
pricing-update/google-24257386432

Conversation

@siddharthsambharia-portkey
Copy link
Copy Markdown
Collaborator

🔄 Pricing Update: google

📊 Summary (complete_diff mode)

Change Type Count
➕ Models added 2
🔄 Models updated (merged) 44

➕ New Models

  • veo-3.1-lite-generate-preview-lte-128k
  • veo-3.1-lite-generate-preview-gt-128k

🔄 Updated Models

  • gemini-2.5-pro-lte-128k
  • gemini-2.5-pro-gt-128k
  • gemini-2.5-flash-lte-128k
  • gemini-2.5-flash-gt-128k
  • gemini-2.5-flash-lite-lte-128k
  • gemini-2.5-flash-lite-gt-128k
  • gemini-2.5-flash-image-lte-128k
  • gemini-2.5-flash-image-gt-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-pro-preview-lte-128k
  • gemini-3.1-pro-preview-gt-128k
  • gemini-3-pro-preview-lte-128k
  • gemini-3-pro-preview-gt-128k
  • gemini-3-flash-preview-lte-128k
  • gemini-3-flash-preview-gt-128k
  • gemini-3.1-flash-lite-preview-lte-128k
  • gemini-3.1-flash-lite-preview-gt-128k
  • gemini-3.1-flash-image-preview-lte-128k
  • gemini-3.1-flash-image-preview-gt-128k
  • gemini-3-pro-image-preview-lte-128k
  • gemini-3-pro-image-preview-gt-128k
  • gemini-pro-latest-lte-128k
  • gemini-pro-latest-gt-128k
  • ... and 14 more

Pricing source note

Pricing data was sourced from the Google Cloud Vertex AI Generative AI pricing page (https://cloud.google.com/vertex-ai/generative-ai/pricing) because the Gemini API pricing page (https://ai.google.dev/gemini-api/docs/pricing) exceeded the inline response size limit and could not be parsed. The Vertex AI page covers the same model families with the same pricing tiers. Vertex AI uses a 200K context threshold; this PR maps ≤200K → -lte-128k and >200K → -gt-128k per skill convention.

Web search/grounding pricing uses the Gemini API standard rate ($3.5/1K calls = 0.35¢/call) per skill examples rather than the Vertex AI rate ($35/1K = 3.5¢/call).

Thinking tokens: On the Vertex AI page, "Text output (response and reasoning)" bundles reasoning into the output price — no separate thinking_token field was added.


Model → pricing page mapping

Model ID Pricing page section Notes
gemini-2.5-pro-lte-128k Gemini 2.5 Pro, ≤200K input $1.25, output $10, cache_read $0.13; batch $0.625/$5
gemini-2.5-pro-gt-128k Gemini 2.5 Pro, >200K input $2.50, output $15, cache_read $0.25; batch $1.25/$7.50
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
gemini-2.5-flash-gt-128k Gemini 2.5 Flash, flat pricing identical to lte — no context tier
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
gemini-2.5-flash-lite-gt-128k Gemini 2.5 Flash Lite, flat pricing identical to lte — no context tier
gemini-2.5-flash-image-lte-128k Gemini 2.5 Flash Image, flat pricing input $0.30, text output $2.50, image_token $30/1M; batch $0.15/$1.25 (text); batch image $15/1M noted
gemini-2.5-flash-image-gt-128k Gemini 2.5 Flash Image, flat pricing identical to lte — no context tier
gemini-2.0-flash-lte-128k Gemini 2.0 Flash, flat pricing input $0.15, output $0.60; batch $0.075/$0.30
gemini-2.0-flash-gt-128k Gemini 2.0 Flash, flat pricing identical to lte — no context tier
gemini-2.0-flash-001-lte-128k Gemini 2.0 Flash (pinned 001), flat same as gemini-2.0-flash
gemini-2.0-flash-001-gt-128k Gemini 2.0 Flash (pinned 001), flat identical to 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
gemini-2.0-flash-lite-gt-128k Gemini 2.0 Flash Lite, flat pricing identical to lte — no context tier
gemini-2.0-flash-lite-001-lte-128k Gemini 2.0 Flash Lite (pinned 001) same as gemini-2.0-flash-lite
gemini-2.0-flash-lite-001-gt-128k Gemini 2.0 Flash Lite (pinned 001) identical to lte
gemini-3.1-pro-preview-lte-128k Gemini 3.1 Pro Preview, ≤200K input $2, output $12, cache_read $0.20; batch $1/$6
gemini-3.1-pro-preview-gt-128k Gemini 3.1 Pro Preview, >200K input $4, output $18, cache_read $0.40; batch $2/$9
gemini-3-pro-preview-lte-128k Gemini 3 Pro Preview, ≤200K input $2, output $12, cache_read $0.20; batch $1/$6
gemini-3-pro-preview-gt-128k Gemini 3 Pro Preview, >200K input $4, output $18, cache_read $0.40; batch $2/$9
gemini-3-flash-preview-lte-128k Gemini 3 Flash Preview, flat pricing input $0.50, output $3, cache_read $0.05; batch $0.25/$1.50
gemini-3-flash-preview-gt-128k Gemini 3 Flash Preview, flat pricing identical to lte — no context tier
gemini-3.1-flash-lite-preview-lte-128k Gemini 3.1 Flash-Lite Preview, flat input $0.25, output $1.50, cache_read $0.03; batch $0.13/$0.75
gemini-3.1-flash-lite-preview-gt-128k Gemini 3.1 Flash-Lite Preview, flat identical to lte — no context tier
gemini-3.1-flash-image-preview-lte-128k Gemini 3.1 Flash Image Preview, flat input $0.50, text output $3, image_token $60/1M; batch $0.25/$1.50 (text); batch image $30/1M noted
gemini-3.1-flash-image-preview-gt-128k Gemini 3.1 Flash Image Preview, flat identical to lte — no context tier
gemini-3-pro-image-preview-lte-128k Gemini 3 Pro Image Preview, flat input $2, text output $12, image_token $120/1M; batch $1/$6 (text)
gemini-3-pro-image-preview-gt-128k Gemini 3 Pro Image Preview, flat identical to lte — no context tier
gemini-pro-latest-lte-128k *-latest → resolved to gemini-3.1-pro-preview same pricing as gemini-3.1-pro-preview lte
gemini-pro-latest-gt-128k *-latest → resolved to gemini-3.1-pro-preview same pricing as gemini-3.1-pro-preview gt
gemini-flash-latest-lte-128k *-latest → resolved to gemini-3-flash-preview same pricing as gemini-3-flash-preview lte
gemini-flash-latest-gt-128k *-latest → resolved to gemini-3-flash-preview same pricing as gemini-3-flash-preview gt
gemini-flash-lite-latest-lte-128k *-latest → resolved to gemini-3.1-flash-lite-preview same pricing as gemini-3.1-flash-lite-preview lte
gemini-flash-lite-latest-gt-128k *-latest → resolved to gemini-3.1-flash-lite-preview same pricing as gemini-3.1-flash-lite-preview gt
gemini-3.1-pro-preview-customtools-lte-128k Not found on pricing page input $0, output $0 — price not listed
gemini-3.1-pro-preview-customtools-gt-128k Not found on pricing page input $0, output $0 — price not listed
gemini-embedding-001-lte-128k Gemini Embedding, flat input $0.15/1M ($0.00015/1K), output 0
gemini-embedding-001-gt-128k Gemini Embedding, flat identical to lte
gemini-embedding-2-preview-lte-128k Gemini Embedding 2 Preview, flat text input $0.20/1M, output 0; image/video/audio pricing not mapped (no token field)
gemini-embedding-2-preview-gt-128k Gemini Embedding 2 Preview, flat identical to lte
imagen-4.0-generate-001-lte-128k Imagen 4, per-image $0.04/image
imagen-4.0-generate-001-gt-128k Imagen 4, per-image identical to lte
imagen-4.0-ultra-generate-001-lte-128k Imagen 4 Ultra, per-image $0.06/image
imagen-4.0-ultra-generate-001-gt-128k Imagen 4 Ultra, per-image identical to lte
imagen-4.0-fast-generate-001-lte-128k Imagen 4 Fast, per-image $0.02/image
imagen-4.0-fast-generate-001-gt-128k Imagen 4 Fast, per-image identical to lte
veo-2.0-generate-001-lte-128k Veo 2, video-only $0.50/s → 50¢/s; default 8s, 1 sample
veo-2.0-generate-001-gt-128k Veo 2, video-only identical to lte
veo-3.0-generate-001-lte-128k Veo 3, video-only 720p/1080p $0.20/s → 20¢/s; default 8s, 1 sample
veo-3.0-generate-001-gt-128k Veo 3, video-only 720p/1080p identical to lte
veo-3.0-fast-generate-001-lte-128k Veo 3 Fast, video-only 720p $0.08/s → 8¢/s; default 8s, 1 sample
veo-3.0-fast-generate-001-gt-128k Veo 3 Fast, video-only 720p identical to lte
veo-3.1-generate-preview-lte-128k Veo 3.1, video-only 720p/1080p $0.20/s → 20¢/s; default 8s, 1 sample
veo-3.1-generate-preview-gt-128k Veo 3.1, video-only 720p/1080p identical to lte
veo-3.1-fast-generate-preview-lte-128k Veo 3.1 Fast, video-only 720p $0.08/s → 8¢/s; default 8s, 1 sample
veo-3.1-fast-generate-preview-gt-128k Veo 3.1 Fast, video-only 720p identical to lte
veo-3.1-lite-generate-preview-lte-128k Veo 3.1 Lite, video-only 720p $0.03/s → 3¢/s; default 8s, 1 sample
veo-3.1-lite-generate-preview-gt-128k Veo 3.1 Lite, video-only 720p identical to lte

Generated by Pricing Agent on 2026-04-10

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