Gemini 3.8 Flash Pricing & Token Costs (2026)
Per 1M tokens: input $0.75 · output $3.75 · cached $0.075. Context window 1,048,576 tokens with source and verification details.
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.
TL;DR — Pricing Quick Summary
- ✓Input pricing: $0.75 per 1M tokens ($0.0008 per 1K)
- ✓Output pricing: $3.75 per 1M tokens ($0.0037 per 1K)
- ✓Prompt caching: $0.075 per 1M tokens — save 90% on repeated context
- ✓Context window: 1,048,576 tokens
- ✓Typical monthly cost: $15.00 for 10M input + 2M output across short requests; Promotional through 2026-12-31 · Developer API
- ✓Daily cost example: $0.2250 for 100K tokens (50K in, 50K out)
Key metrics
- Context window
- 1,048,576 tokens
- Input price
- $0.75 / 1M tokens
- Output price
- $3.75 / 1M tokens
- Cached input
- $0.075 / 1M tokens
Official link:https://ai.google.dev/gemini-api/docs/pricing
Last verified: 2026-10-07
- · 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.
Multi-currency (per 1M tokens)
| Currency | Input | Cached | Output |
|---|---|---|---|
| USD | $0.75 | $0.08 | $3.75 |
| CNY | ¥5.36 | ¥0.54 | ¥26.81 |
| EUR | 0,69 € | 0,07 € | 3,45 € |
| JPY | ￥110 | ￥11 | ￥548 |
* Live search cost uses sources / 1000 × price and currently applies to xAI Grok only.
Frequently Asked Questions
What is the cost per 1M tokens for Google Gemini 3.8 Flash?
Google Gemini 3.8 Flash costs $0.75 per 1M input tokens and $3.75 per 1M output tokens, with cached input at $0.075 per 1M tokens.
How much does it cost per 1K tokens?
Per 1K tokens: $0.0008 for input and $0.0037 for output. This is useful for calculating costs for smaller workloads or individual API calls.
What is the estimated monthly cost for typical usage?
For 10M input + 2M output tokens per month across requests within the short-context tier, Google Gemini 3.8 Flash would cost approximately $15.00. Daily usage of 100K tokens (50K in, 50K out) costs about $0.2250.
Does Google Gemini 3.8 Flash offer a free tier?
Check Google's official documentation for free tier availability. Some providers offer free credits for new users or limited free usage. Visit https://ai.google.dev/gemini-api/docs/pricing for current free tier details.
How does prompt caching work to reduce costs?
With prompt caching enabled, input pricing drops to $0.075 per 1M tokens for repeated context (a 90% discount), while output remains $3.75 per 1M tokens. Caching is ideal for repeated prompts or system messages.
What is the context window size for Gemini 3.8 Flash?
Gemini 3.8 Flash supports a 1,048,576 token context window. This determines the maximum combined length of your input prompt and output response.
How frequently is this pricing information updated?
All prices reference official Google documentation (https://ai.google.dev/gemini-api/docs/pricing), last verified on 2026-10-07. Review the source before budgeting; other catalog entries may have older verification dates.
How can I calculate exact costs for my use case?
Use our free token calculator to estimate costs based on your specific usage pattern. The calculator supports all major models and shows costs in multiple currencies. You can also compare costs across different models to find the most economical option.