Frontier model API
How Google Gemini API compares
Gemini Developer API. Standard paid rates, including prices that the page says change on a stated date.
Regions and compliance
Regions: not published / unverified
Compliance: not published / unverified
Other published facts
- Batch API: 0.5ai.google.devchecked 2026-10-20
Token offerings
Gemini 4 Argon (through 30 Nov 2026)
serverless_api · gemini-4-argon · open-weight not published / unverified
- Input / 1M
- 2ai.google.devchecked 2026-10-20“Input price | Paid Tier | $2.00 through November 30, 2026. $4.00 starting December 1, 2026.”
- Cached input / 1M
- 0.1ai.google.devchecked 2026-10-20“Context caching price | $0.10 through November 30, 2026. $0.20 starting December 1, 2026. Implicit caching only.”
- Output / 1M
- 10ai.google.devchecked 2026-10-20“Output price (including thinking tokens) | $10.00 through November 30, 2026. $20.00 starting December 1, 2026.”
Context not published · tokens/s not published · TTFT not published
Price in effect on the check date. The same cells publish a higher rate starting 1 Dec 2026.
Gemini 3.8 Flash (through 31 Dec 2026)
serverless_api · gemini-3.8-flash · open-weight not published / unverified
- Input / 1M
- 0.75ai.google.devchecked 2026-10-20“Input price | $0.75 through December 31, 2026. $1.50 starting January 1, 2027.”
- Cached input / 1M
- 0.075ai.google.devchecked 2026-10-20“Context caching price | $0.075 through December 31, 2026. $0.15 starting January 1, 2027.”
- Output / 1M
- 3.75ai.google.devchecked 2026-10-20“Output price (including thinking tokens) | $3.75 through December 31, 2026. $7.50 starting January 1, 2027.”
Context not published · tokens/s not published · TTFT not published
Standard paid tier on the check date. Storage price for cache is separate and not included in the per-token figure.
Gemini 3.1 Flash-Lite
serverless_api · gemini-3.1-flash-lite · open-weight not published / unverified
- Input / 1M
- 0.25ai.google.devchecked 2026-10-20“Input price | $0.25 (text / image / video) $0.50 (audio)”
- Cached input / 1M
- 0.025ai.google.devchecked 2026-10-20“Context caching price | $0.025 (text / image / video) $0.05 (audio)”
- Output / 1M
- 1.5ai.google.devchecked 2026-10-20“Output price (including thinking tokens) | $1.50”
Context not published · tokens/s not published · TTFT not published
Text, image, and video input rate. Audio input is $0.50 per 1M on the same row.
Compute SKUs
No GPU or node price is seeded.