Google AI Studio / Gemini APIVerified 2026-11-12
Gemini 4 Carbon API Pricing & Cost Rules
API Model ID: gemini-4-carbon · Context Window: 1,048,576 tokens · Max Output: 65,536 tokens
Promotional Rate Alert: Current pricing expires on 2026-11-30. Confirm post-promotional rates before locking long-term production budgets.
Context Tiers & Token Rate Card (USD per 1M Tokens)
| Tier | Std Input | Std Output | Cache Read | Write (Short) | Write (Long) |
|---|---|---|---|---|---|
| Intro Promo (<= 1M, thru 2026-11-30) | $2.00 | $10.00 | $0.1 | $2.00 | N/A |
Prompt Caching Rules
Supported: Yes (automatic)
Minimum Cacheable Prefix: 4,096 tokens
Hourly Cache Storage: $0
Implicit caching ONLY (explicit caching not supported on Gemini 4). Min 4,096 tokens. Multi-turn only caches full prior request if new turn adds >= 2,050 tokens.
Batch API & Hosting Notes
Batch Supported: Yes (50% discount · Up to 24h)
Caching in Batch: Allowed + Batch discount stacks onto cache reads
50% off input ($1.00), output ($5.00), and implicit cache read ($0.05) thru 2026-11-30; doubles 2026-12-01 ($2/$10/$0.10). Paid tier only.
Paid tier only; 65,536 sync max output (long-decode up to 1,048,576). Priority tier = 1.8x ($3.60/$18.00/$0.18 thru Nov 30).