Model lab
Google Gemini API
API prices for every model
ai.google.dev
- Models
- 29
- Cheapest
- $0.05
- Gemma 3 4B input
- Also sold by
- 22
- other providers
- Batch
- Yes
- see note below
Google Gemini API on the price map
Size: context window, 8K to 2MEqual blended cost (3:1) 243 models, lower left is cheaper
Every model
ModelInputOutputCachedContextReleased
Gemini 3.8 FlashGoogle Gemini API · 1M$0.75 / $3.75in / out per 1M$0.75$3.75$0.0751MSep 2, 2026
Gemini 3.7 FlashGoogle Gemini API · 1M$0.75 / $3.75in / out per 1M$0.75$3.75$0.0751MAug 13, 2026
Gemini 3.5 Flash LiteGoogle Gemini API · 1M$0.3 / $2.5in / out per 1M$0.3$2.5$0.031MJul 21, 2026
Gemini 3.6 FlashGoogle Gemini API · 1M$0.75 / $3.75in / out per 1M$0.75$3.75$0.0751MJul 21, 2026
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google Gemini API · 66K$0.25 / $1.5in / out per 1M$0.25$1.5n/a66KJun 30, 2026
Nano Banana 2 (Gemini 3.1 Flash Image)Google Gemini API · 131K$0.5 / $3in / out per 1M$0.5$3n/a131KJun 18, 2026
Nano Banana Pro (Gemini 3 Pro Image)Google Gemini API · 131K$2 / $12in / out per 1M$2$12$0.2131KJun 18, 2026
Gemini Embedding 2Google Gemini API · 8K$0.2 / Freein / out per 1M$0.2Freen/a8KMay 20, 2026
Gemini 3.5 FlashGoogle Gemini API · 1M$1.5 / $9in / out per 1M$1.5$9$0.151MMay 19, 2026
Gemini 3.1 Flash LiteGoogle Gemini API · 1M$0.25 / $1.5in / out per 1M$0.25$1.5$0.0251MMay 7, 2026
Gemini Embedding 2 PreviewGoogle Gemini API · 8K$0.2 / Freein / out per 1M$0.2Freen/a8KApr 17, 2026
Gemma 4 26B A4BGoogle Gemini API · via Darkbloom · 262K$0.042 / $0.22in / out per 1M$0.042$0.22n/a262KApr 3, 2026
Gemma 4 31BGoogle Gemini API · via DeepInfra (turbo) · 262K$0.09 / $0.34in / out per 1M$0.09$0.34$0.05262KApr 2, 2026
Gemini 3.1 Flash Lite PreviewGoogle Gemini API · 1M$0.25 / $1.5in / out per 1M$0.25$1.5$0.0251MMar 3, 2026
Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google Gemini API · 66K$0.5 / $3in / out per 1M$0.5$3n/a66KFeb 26, 2026
Gemini 3.1 Pro Preview Custom ToolsGoogle Gemini API · 1M$2 / $12in / out per 1M$2$12$0.21MFeb 25, 2026
Gemini 3.1 Pro PreviewGoogle Gemini API · 1M$2 / $12in / out per 1M$2$12$0.21MFeb 19, 2026
Gemini 3 Flash PreviewGoogle Gemini API · 1M$0.5 / $3in / out per 1M$0.5$3$0.051MDec 17, 2025
Nano Banana Pro (Gemini 3 Pro Image Preview)Google Gemini API · 66K$2 / $12in / out per 1M$2$12$0.266KNov 20, 2025
Gemini Embedding 001Google Gemini API · 20K$0.15 / Freein / out per 1M$0.15Freen/a20KOct 31, 2025
Nano Banana (Gemini 2.5 Flash Image)Google Gemini API · 33K$0.3 / $2.5in / out per 1M$0.3$2.5$0.0333KOct 7, 2025
Gemini 2.5 Flash LiteGoogle Gemini API · 1M$0.1 / $0.4in / out per 1M$0.1$0.4$0.011MJul 22, 2025
Gemini 2.5 FlashGoogle Gemini API · 1M$0.3 / $2.5in / out per 1M$0.3$2.5$0.031MJun 17, 2025
Gemini 2.5 ProGoogle Gemini API · 1M$1.25 / $10in / out per 1M$1.25$10$0.1251MJun 17, 2025
Gemini 2.5 Pro Preview 06-05Google Gemini API · 1M$1.25 / $10in / out per 1M$1.25$10$0.1251MJun 5, 2025
Gemma 3 12BGoogle Gemini API · via DeepInfra (bf16) · 131K$0.05 / $0.15in / out per 1M$0.05$0.15n/a131KMar 13, 2025
Gemma 3 4BGoogle Gemini API · via DeepInfra (bf16) · 131K$0.05 / $0.1in / out per 1M$0.05$0.1n/a131KMar 13, 2025
Gemma 3 27BGoogle Gemini API · via DeepInfra (fp8) · 131K$0.08 / $0.16in / out per 1M$0.08$0.16n/a131KMar 12, 2025
Gemma 2 27BGoogle Gemini API · via NextBit (int4) · 8K$0.65 / $0.65in / out per 1M$0.65$0.65n/a8KJul 13, 2024
Google Gemini API models on other routes
Gemma 3 4BDeepInfra, bf16, bf16$0.05 / $0.1
Gemma 3 12BDeepInfra, bf16, bf16$0.05 / $0.15
- Gemma 4 26B A4BDarkbloom$0.042 / $0.22
Gemini 2.5 Flash LiteGoogle Gemini API, flex$0.05 / $0.2-50% vs headline
Gemma 3 27BDeepInfra, fp8, fp8$0.08 / $0.16
Gemini Embedding 001Google Vertex AI, us-central1$0.15 / Free
- Gemma 4 26B A4BDekaLLM, bf16, bf16$0.06 / $0.33+47% vs headline
Gemma 4 26B A4BDeepInfra, fp8, fp8$0.07 / $0.34+59% vs headline
Gemma 3 27BNovita AI, bf16, bf16$0.119 / $0.2+39% vs headline
- Gemma 4 26B A4BNextBit, bf16, bf16$0.09 / $0.3+65% vs headline
Gemma 4 26B A4BCloudflare Workers AI$0.1 / $0.3+73% vs headline
Gemma 4 26B A4BCoreWeave, bf16, bf16$0.1 / $0.3+73% vs headline
Gemma 3 27BNebius, fp8, fp8$0.1 / $0.3+50% vs headline
Gemini Embedding 2Google Vertex AI, global$0.2 / Free
Gemini Embedding 2Google Vertex AI, us$0.2 / Free
Gemma 4 31BDeepInfra, turbo, fp4$0.09 / $0.34
- Gemma 4 26B A4BMakora$0.1 / $0.34+85% vs headline
Gemma 4 31BCoreWeave, fp4, fp4$0.1 / $0.34+5% vs headline
Gemini Embedding 2Google Vertex AI, eu$0.22 / Free+10% vs headline
Gemma 3 27BParasail, fp8, fp8$0.08 / $0.45+72% vs headline
Gemini 2.5 Flash LiteGoogle Vertex AI$0.1 / $0.4
Gemini 2.5 Flash LiteGoogle Vertex AI, eu$0.1 / $0.4
Gemma 4 31BVenice, fp4, fp4$0.12 / $0.36+18% vs headline
Gemma 4 31BChutes, fp4, fp4$0.12 / $0.37+20% vs headline
Gemma 4 31BDeepInfra, fp8, fp8$0.13 / $0.38+26% vs headline
Gemma 4 26B A4BNovita AI, bf16, bf16$0.13 / $0.4+128% vs headline
Gemma 4 26B A4BParasail, bf16, bf16$0.13 / $0.4+128% vs headline
Gemma 4 26B A4BVenice, bf16, bf16$0.13 / $0.4+128% vs headline
Gemma 4 26B A4BSiliconFlow, fp8, fp8$0.14 / $0.4+137% vs headline
Gemma 4 31BCrusoe, bf16, bf16$0.14 / $0.4+34% vs headline
Gemma 4 31BFriendli$0.14 / $0.4+34% vs headline
Gemma 4 31BNovita AI, bf16, bf16$0.14 / $0.4+34% vs headline
Gemma 4 31BParasail, fp8, fp8$0.15 / $0.4+39% vs headline
Gemma 4 26B A4BGoogle Vertex AI, global$0.15 / $0.6+203% vs headline
Gemini 3.1 Flash LiteGoogle Vertex AI, global-flex$0.125 / $0.75-50% vs headline
Gemini 3.1 Flash LiteGoogle Gemini API, flex$0.125 / $0.75-50% vs headline
Gemini 3.1 Flash Lite PreviewGoogle Gemini API, flex$0.125 / $0.75-50% vs headline
Gemini 2.5 Flash LiteGoogle Gemini API, priority$0.18 / $0.72+80% vs headline
Gemma 4 31BDeepInfra, ultra, fp8$0.27 / $0.76+157% vs headline
Gemini 3.5 Flash LiteGoogle Vertex AI, global-flex$0.15 / $1.25-50% vs headline
Gemini 3.5 Flash LiteGoogle Gemini API, flex$0.15 / $1.25-50% vs headline
Nano Banana (Gemini 2.5 Flash Image)Google Gemini API, flex$0.15 / $1.25-50% vs headline
Gemini 2.5 FlashGoogle Gemini API, flex$0.15 / $1.25-50% vs headline
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google Vertex AI, global$0.25 / $1.5
Gemini 3.1 Flash LiteGoogle Vertex AI, global$0.25 / $1.5
Gemini 3 Flash PreviewGoogle Vertex AI, global-flex$0.25 / $1.5-50% vs headline
Gemini 3 Flash PreviewGoogle Gemini API, flex$0.25 / $1.5-50% vs headline
Gemma 4 31BSambaNova$0.38 / $1.15+275% vs headline
Gemini 3.1 Flash LiteGoogle Vertex AI, eu$0.275 / $1.65+10% vs headline
Gemini 3.1 Flash LiteGoogle Vertex AI, us$0.275 / $1.65+10% vs headline
- Gemma 2 27BNextBit, int4, int4$0.65 / $0.65
Gemini 3.8 FlashGoogle Vertex AI, global-flex$0.375 / $1.88-50% vs headline
Gemini 3.8 FlashGoogle Gemini API, flex$0.375 / $1.88-50% vs headline
Gemini 3.7 FlashGoogle Vertex AI, global-flex$0.375 / $1.88-50% vs headline
Gemini 3.7 FlashGoogle Gemini API, flex$0.375 / $1.88-50% vs headline
Gemini 3.6 FlashGoogle Vertex AI, global-flex$0.375 / $1.88-50% vs headline
Gemini 3.6 FlashGoogle Gemini API, flex$0.375 / $1.88-50% vs headline
- Gemma 4 31BModelRun, fp4, fp4$0.75 / $1+433% vs headline
Gemma 4 31BSiliconFlow, fp8, fp8$0.75 / $1+433% vs headline
Gemini 3.5 Flash LiteGoogle Vertex AI, global$0.3 / $2.5
Nano Banana (Gemini 2.5 Flash Image)Google Vertex AI, global$0.3 / $2.5
Gemini 2.5 FlashGoogle Vertex AI$0.3 / $2.5
Gemini 2.5 FlashGoogle Vertex AI, eu$0.3 / $2.5
Gemini 2.5 FlashGoogle Vertex AI, global$0.3 / $2.5
Gemini 2.5 FlashOCI Generative AI, $0.30 / $2.50 per 1,000,000 tokens$0.3 / $2.5
Gemini 3.5 Flash LiteGoogle Vertex AI, eu$0.33 / $2.75+10% vs headline
Gemini 3.5 Flash LiteGoogle Vertex AI, us$0.33 / $2.75+10% vs headline
Gemini 3.1 Flash LiteGoogle Vertex AI, global-priority$0.45 / $2.7+80% vs headline
Gemini 3.1 Flash LiteGoogle Gemini API, priority$0.45 / $2.7+80% vs headline
Gemini 3.1 Flash Lite PreviewGoogle Gemini API, priority$0.45 / $2.7+80% vs headline
Nano Banana 2 (Gemini 3.1 Flash Image)Google Vertex AI, global$0.5 / $3
Gemini 3 Flash PreviewGoogle Vertex AI, global$0.5 / $3
Gemini 3.8 FlashGoogle Vertex AI, global$0.75 / $3.75
Gemini 3.7 FlashGoogle Vertex AI, global$0.75 / $3.75
Gemini 3.6 FlashGoogle Vertex AI, global$0.75 / $3.75
Gemini 3.5 Flash LiteGoogle Vertex AI, global-priority$0.54 / $4.5+80% vs headline
Gemini 3.5 Flash LiteGoogle Gemini API, priority$0.54 / $4.5+80% vs headline
Nano Banana (Gemini 2.5 Flash Image)Google Gemini API, priority$0.54 / $4.5+80% vs headline
Gemini 2.5 FlashGoogle Vertex AI, global-priority$0.54 / $4.5+80% vs headline
Gemini 2.5 FlashGoogle Gemini API, priority$0.54 / $4.5+80% vs headline
Notes from the pricing page
Batch: Batch pricing is 50% of standard in the tables
Caching: Context caching at 10% of the input price for most models, plus storage $0.50 / 1M tokens per hour through Dec 31, 2026 ($1.00 after)
Google LLC is an American multinational technology corporation focused on information technology, online advertising, search engine technology, email, cloud computing, software, quantum computing, e-commerce, consumer electronics, and artificial intelligence (AI).
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.