LLM API pricing
Gemini 2.5 Flash vs Gemini 3.8 Flash: price per 1M tokens
Updated 2026-10-14
Gemini 2.5 Flash costs $0.3 / $2.50 per 1M input/output tokens (Google API (direct)) vs $0.75 / $3.75 for Gemini 3.8 Flash (Google API (direct)). Blended 3:1, Gemini 2.5 Flash is -43% vs Gemini 3.8 Flash.
Gemini 2.5 Flash by channel
| Channel | Input | Output | Cache read | Paid with |
|---|---|---|---|---|
| Google API (direct) | $0.3 | $2.50 | $0.03 | card billing (no cloud credits) |
| Google Vertex AI (Standard, Global, <=200K ctx) | $0.3 | $2.50 | $0.03 | Google Cloud credits |
Gemini 3.8 Flash by channel
| Channel | Input | Output | Cache read | Paid with |
|---|---|---|---|---|
| Google API (direct) | $0.75 | $3.75 | $0.075 | card billing (no cloud credits) |
| Google Vertex AI (Standard, Global, <=200K ctx) | $0.75 | $3.75 | $0.075 | Google Cloud credits |
Worked examples (monthly bill at list price)
| Workload | Gemini 2.5 Flash | Gemini 3.8 Flash | Difference |
|---|---|---|---|
| Support chatbot: 100,000 × 1,000 in / 300 out | $105.00 | $187.50 | -44% |
| RAG over docs: 50,000 × 4,000 in / 500 out | $122.50 | $243.75 | -50% |
| Coding agent: 200,000 × 20,000 in / 2,000 out | $2,200.00 | $4,500.00 | -51% |
Tokens per $25,000 of credits
- Gemini 2.5 Flash via Google Vertex AI (Standard, Global, <=200K ctx) (Google Cloud credits): 29.41B tokens
- Gemini 3.8 Flash via Google Vertex AI (Standard, Global, <=200K ctx) (Google Cloud credits): 16.67B tokens
More
Cost calculator
Monthly bill: $105
Paid with Google Cloud credits: 238.1 months of runway.
Related cost calculators
- Amazon Bedrock AgentCore Pricing Calculator · Runtime, Gateway, Memory & Policy Costs
- Bedrock Pricing Calculator · AI Model & Tool Cost Estimator
- Amazon SageMaker AI Pricing Calculator · On-Demand Studio, Training & Inference
Prices and credit amounts are estimates and may change. Check AWS for current terms.