Verified 2026-10-07 · sourced from Google
100K Gemini 3.8 Flash Tokens — Cost Breakdown
Use this guide to benchmark budgets for 100,000 tokens. Standard pricing is $0.75 per million input tokens and $3.75 per million output tokens. Cached input, when available, reduces costs significantly for repeated contexts.
Reference rates: Promotional through 2026-12-31 · Developer API
USD per million text tokens. Verified 2026-10-07 · Official source
| Mode / prompt size | Input | Cache read | Cache write | Output |
|---|---|---|---|---|
| Standard | $0.75 | $0.075 | Not estimated | $3.75 |
| Batch | $0.375 | $0.0375 | Not estimated | $1.875 |
Cache storage: $0.5 per million tokens per hour, charged separately and excluded from the per-call estimate.
1,048,576 context tokens · max output 65,536. Local token counts are estimates; use the provider’s usage counts for an invoice estimate.
Text-only estimate. Local token counts are approximate; use provider-reported usage for billing. Tool, image, audio and video charges are excluded.
Gemini Developer API paid-tier text rates (not Vertex AI). Output includes thinking tokens. Cache storage is billed separately by token-hours; grounding and tools cost extra.
Promotion: standard $0.75 input / $0.075 cache read / $3.75 output through 2026-12-31. From 2027-01-01: $1.50 / $0.15 / $7.50. Batch $0.375 / $0.0375 / $1.875 becomes $0.75 / $0.075 / $3.75. Storage rises from $0.50 to $1 per million token-hours. Calculator switches at 00:00 UTC on 2027-01-01.
Scenario breakdown
Cost estimates for different input/output distributions using 100K total tokens.
| Scenario | Tokens in | Tokens out | Standard cost | Cached cost |
|---|---|---|---|---|
Balanced conversation 50% input · 50% output | 50,000 | 50,000 | $0.225 | $0.191 |
Input-heavy workflow 80% input · 20% output | 80,000 | 20,000 | $0.135 | $0.0810 |
Generation heavy 30% input · 70% output | 30,000 | 70,000 | $0.285 | $0.265 |
Cached system prompt 90% cached input · 10% fresh output | 90,000 | 10,000 | $0.105 | $0.0442 |
Workload multipliers
Convert 100K tokens into daily and monthly run-rate budgets.
| Profile | Runs/day | Tokens/day | Daily cost | Monthly cost | Cached daily | Cached monthly |
|---|---|---|---|---|---|---|
| Single workload | 1 | 100,000 | $0.225 | $6.75 | $0.0442 | $1.33 |
| Daily batch (10 runs) | 10 | 1,000,000 | $2.25 | $67.50 | $0.443 | $13.28 |
| Team workload (100 runs) | 100 | 10,000,000 | $22.50 | $675.00 | $4.42 | $132.75 |
Frequently asked questions
What is the standard cost of 100K Gemini 3.8 Flash tokens?
100K tokens in a 50/50 conversation mix cost roughly $0.225 at the published Google rates.
What happens if cached input is enabled?
With cached contexts, the same 100K tokens drop to $0.191 because input costs fall to $0.075 per million tokens.
How many requests does 100K tokens cover?
If your prompts average around 3,000 tokens per call, 100K total tokens cover about 33 requests.
How fresh is the pricing information?
Prices are taken from https://ai.google.dev/gemini-api/docs/pricing and were last verified on 2026-10-07. models.json keeps this guide in sync with upstream changes.