🏢

EmbeddingGemma 2 API Pricing / Price per 1M tokens

Multimodal embeddings of text, images, video and audio in one 768-dimensional space on Workers AI. Workers AI id @cf/google/embeddinggemma-2. Open multimodal embedding model from Google DeepMind. Default vector size 768 dimensions; optional shorter sizes 128, 256 or 512 via the dimensions parameter. Context window 8,192 tokens, shared across all content in an input. Unit price $0.0017 per million input tokens on the official model page and changelog (2026-11-12). No official Google API list price is stored. This is a Cloudflare-hosted channel, not a Google first-party listing. Sources verified 2026-11-14. Sources: Cloudflare: https://developers.cloudflare.com/workers-ai/models/embeddinggemma-2/ | Cloudflare: https://developers.cloudflare.com/changelog/post/2026-11-12-embeddinggemma-2-workers-ai/

Cloudflare • API Price Comparison

Also known as: cloudflare-embeddinggemma-2 · cloudflare embeddinggemma 2 · cloudflareembeddinggemma2 · cloudflare-embeddinggemma2 · cloudflare embeddinggemma2 · embeddinggemma-2 · embeddinggemma2

API pricing and token costs at a glance

Updated on · Published currencies / per 1M tokens; cheapest ranked by input

Official and cheapest channel API pricing
ChannelInput / 1MOutput / 1MCache read / 1MUpdated / verified on
CloudflareOfficialLowest inputUSD 0.0017——2026-11-14

Metered API cost = input tokens / 1M × input rate + output tokens / 1M × output rate. No complete input/output quote is available for a total-cost example. This excludes caching, tools, retries and other service fees; the lowest input rate does not guarantee the lowest total bill.

— means the price or date is not recorded. Cross-currency ranking uses exchange rates.

📏 Context: 8,192 tokensAdded Nov 14, 2026

EmbeddingGemma 2 is a large language model by Cloudflare with a 8K-token context window. Across the 1 API channels tracked here, input pricing ranges from $0.00 per 1M input tokens; the cheapest is Cloudflare at $0.00 per 1M input tokens. The official channel (Cloudflare) charges $0.00 per 1M input tokens and $0.00 per 1M output tokens. Prices are collected daily from official provider pages and every tracked channel, then cross-checked by a data-accuracy audit.

💰 Cheapest Option
Cloudflare
$0.00/1M input
-/1M output
Visit website
🏢 Official Price
Cloudflare
$0.00/1M input
-/1M output
Visit website
📊 Channel Price Comparison
Compare EmbeddingGemma 2 API prices across all available channels • 1 channels available
ChannelTypeInput / 1MOutput / 1MRate Limitvs Official
Cloudflare💰 Best Price🏢 Official
Official$0.00--Baseline
📈 Price History
Every scraper-detected price change is recorded. Same-day multiple changes take the last value; unchanged channels carry the last observed price forward.
No price history yet. New price changes will appear after the next scraper run.
💵 Estimated Monthly Costs
Based on typical usage patterns (input:output = 2:1 ratio); all channels converted to USD for comparison
Usage LevelTokens/MonthCloudflare
🐣 Light0.1M in + 0.1M out-
📊 Medium1.0M in + 0.5M out-
🚀 Heavy10.0M in + 5.0M out-
🏢 Enterprise100.0M in + 50.0M out-

Frequently asked questions about EmbeddingGemma 2

How much does the EmbeddingGemma 2 API cost?

The lowest input rate is USD 0.0017 per 1M tokens; output on that channel is — per 1M tokens.

Which channel has the cheapest EmbeddingGemma 2 API?

Cloudflare has the lowest input rate: USD 0.0017 per 1M tokens. Cross-currency ranking uses exchange rates; compare output and cache prices separately.

What is the EmbeddingGemma 2 cache-read price?

No cache-read rate is recorded; missing prices do not imply free caching.

When was EmbeddingGemma 2 pricing last updated?

Updated on 2026-11-14. This is the latest recorded price update or verification; see the table for individual channel dates.

Is there a free EmbeddingGemma 2 API?

No available recorded channel lists both input and output at zero. Missing prices, free cache reads or a free chat tier do not establish a free API; check provider terms for trial credits.

How do I calculate EmbeddingGemma 2 token costs and monthly spend?

Metered API cost = input tokens / 1M × input rate + output tokens / 1M × output rate. No complete input/output quote is available for a total-cost example. This excludes caching, tools, retries and other service fees; the lowest input rate does not guarantee the lowest total bill.

Related models from the same producer