{T}
TokenMath.net
Verified against Google Cloud / AI Studio Pricing
GoogleflagshipGenerally AvailableActive Production

Gemini 3.8 Pro Token Counter & Cost Calculator

Generally available flagship with 1M native context and tiered >200k long-context pricing

Standard Input / 1M
$4.00
Prompt tokens
Cached Input / 1M
$0.40
Prompt caching rate
Output / 1M
$18.00
Generation completion
Context Window
1.05M
Max out: 64k
Tiered Context Pricing
Standard Prompts (≤ 200k)
$4.00 in / $18.00 out
Cached: $0.40/1M
Long-Context Prompts (> 200k)
$8.00 in / $27.00 out
Cached: $0.80/1M
API & Developer Integration Details
generally available
API Model Stringgemini-3.8-pro-001
Provider & FamilyGoogle (gemini)
Prompt Caching Rules32,768 min tokens (90% off)
Long-Context Tiers> 200k: 2x in / 1.5x out
First-party audit timestamp: 2026-09-23 04:43 UTCOfficial Documentation

Interactive Cost & Token Simulator for Gemini 3.8 Pro

Live Calculation
Input Tokens2,500
Output Tokens800
Requests / Day5,000
Prompt Caching Ratio (50%)$0.4/M cached rate
Cost / Request$0.0199
Daily Spend (5,000 reqs)$99.50
Monthly Run-Rate (30d)$2,985.00

Standard Workload Cost Scenarios

ScenarioInput TokensOutput TokensUncached CostWith Prompt Caching
Short Chat Query1,000500$0.0130$0.00940
Document Summarization10,0002,000$0.0760$0.0400
Codebase & Context Analysis100,00020,000$0.7600$0.4000
Batch Corpus Processing1,000,000100,000$5.80$2.20
Technical Architecture & Pricing VerificationVerified: 2026-09-23 04:43 UTC
Model ArchitectureGemini 3.8 Pro
Provider OrganizationGoogle
Tokenizer EncodingGoogle Gemini SentencePiece (256k vocabulary)
API ConnectivityGoogle AI Studio & Vertex AI API. GA successor to Gemini 3.1 Pro Preview.
Batch API 50% DiscountSupported (50% off input & output)
0
Tier 1 Rate Quota (Free-Tier Reference)2,000 RPM · 4M TPM

Tier 1 (free tier) reference limits — your account's actual quota may be higher.

Blended 3:1 Cost / 1M Tokens$7.50
Long-context step function: prompt input above 200,000 tokens bills 2.0x input ($8.00/1M) and 1.5x output ($27.00/1M). Context caching has no write surcharge; storage bills $0.50/1M/hr promo through Dec 31, 2026. Cached reads discount 90% ($0.40/1M).Google Cloud / AI Studio Pricing

Verified Pricing History

September 2026: $4/M input · $18/M output ($0.4/M cached)
Gemini 3.8 Pro general availability with >200k tiered pricing.

When to Choose Gemini 3.8 Pro

Ideal for production workloads demanding flagship capabilities, deep context depth (1.05M tokens), and reliability from Google. Excellent when predictable tokenomics and prompt caching support are paramount.

When Another Model May Be Better

If your use-case requires sub-second streaming latency or ultra-high frequency classification at micro-cent pricing, consider lighter budget options such as Gemini Flash-Lite or Claude Haiku. For deep formal logic, consider dedicated reasoning models like o3.

Frequently Asked Questions About Gemini 3.8 Pro

How much does 1 million tokens cost with Gemini 3.8 Pro?

For Gemini 3.8 Pro, 1 million input tokens costs $4.00, while 1 million output tokens costs $18.00. If using prompt caching, repetitive input prefixes are discounted to $0.40 per million.

What is the context window for Gemini 3.8 Pro?

Gemini 3.8 Pro features a maximum context window of 1,048,576 tokens (~786,432 words), with a maximum output limit of 65,536 tokens per completion.

Which tokenizer does Gemini 3.8 Pro use?

Gemini 3.8 Pro utilizes the Google Gemini SentencePiece (256k vocabulary). Token counting on TokenMath runs client-side to ensure maximum privacy.

Does Gemini 3.8 Pro support prompt caching discounts?

Yes. Gemini 3.8 Pro supports prompt caching with a cached input rate of $0.40/1M (saving up to 90% on repeated input context).