Pricing / Google Gemini

Google Gemini API pricing

50 model entries. Google Gemini entries in the bundled pricing snapshot. Source rate fields are shown as encoded in the snapshot dated 2026-03-25; model modality is not encoded.

Lowest encoded input rate

$0.0375/1M

gemini-flash-1.5-8b

Highest encoded input rate

$15/1M

claude-4-opus

Models with cache pricing

32 of 50

Interpret the /1M columns as token rates only for models independently verified as token-billed. Non-text billing units are not represented in this snapshot schema.

ModelInput $/1MOutput $/1MCache $/1M
gemini-flash-1.5-8b$0.0375$0.15$0.01
gemini-1.5-flash$0.075$0.3$0.01875
gemini-2.0-flash-lite$0.075$0.3-
gemini-flash-1.5$0.075$0.3$0.01875
gemini-2.0-flash-lite-001$0.075$0.3$0.0187
gemini-2.0-flash$0.1$0.4$0.025
gemini-2.5-flash-lite$0.1$0.4$0.01
gemini-2.0-flash-001$0.1$0.4$0.025
gemini-2.5-flash-lite-preview-09-2025$0.1$0.4$0.01
gemini-flash-lite-latest$0.1$0.4$0.025
gemini-2.5-flash-lite-preview-06-17$0.1$0.4$0.025
gemini-1.0-pro-vision-001$0.125$0.375-
gemini-pro$0.125$0.375-
gemini-2.5-flash-preview$0.15$0.6-
claude-3-haiku$0.25$1.25$0.03
gemini-3.1-flash-lite-preview$0.25$1.5$0.025
gemini-2.5-flash$0.3$2.5$0.03
gemini-2.5-flash-image$0.3$30-
gemini-live-2.5-flash-preview-native-audio-09-2025$0.3$2$0.075
gemini-robotics-er-1.5-preview$0.3$2.5-
gemini-2.5-flash-preview-09-2025$0.3$2.5$0.075
gemini-flash-latest$0.3$2.5$0.075
gemini-2.5-flash-preview-tts$0.3$2.5-
gemini-2.5-flash-native-audio-latest$0.3$2.5-
gemini-2.5-flash-native-audio-preview-09-2025$0.3$2.5-
gemini-2.5-flash-native-audio-preview-12-2025$0.3$2.5-
gemini-exp-1206$0.3$2.5$0.03
gemini-gemma-2-27b-it$0.35$1.05-
gemini-gemma-2-9b-it$0.35$1.05-
gemini-3-flash-preview$0.5$3$0.05
gemini-3.1-flash-image-preview$0.5$60-
gemini-live-2.5-flash-preview$0.5$2-
claude-3-5-haiku$0.8$4$0.08
gemini-2.5-pro$1.25$10$0.125
gemini-1.5-pro$1.25$5-
gemini-pro-1.5$1.25$5$0.3125
gemini-2.5-computer-use-preview-10-2025$1.25$10-
gemini-2.5-pro-preview-tts$1.25$10$0.125
gemini-pro-latest$1.25$10$0.125
gemini-3-pro-image-preview$2$120-
gemini-3-pro-preview$2$12$0.2
gemini-3.1-pro-preview$2$12$0.2
deep-research-pro-preview-12-2025$2$12-
gemini-3.1-pro-preview-customtools$2$12$0.2
claude-3-5-sonnet$3$15$0.3
claude-3-7-sonnet$3$15$0.3
claude-4-sonnet$3$15$0.3
claude-opus-4-6$5$25$0.5
claude-3-opus$15$75$1.5
claude-4-opus$15$75$1.5

Use the Google Gemini snapshot as a reference, then measure the request

Local tracking can estimate supported responses from provider usage fields. The authenticated gateway path adds request identity, persisted cost evidence, session attribution, and pre-dispatch budget checks.