Gemini 3.8 Flash Batch API Cost Calculator
Calculate high-volume asynchronous data processing, bulk document indexing, and tagging expenses using Gemini 3.8 Flash Batch API (50% discount).
Describe Your Workload
= 300,000 requests a month (30 days)
System prompt + chat history + retrieved documents + the user's message.
Count too: they bill as output.
Rule of thumb for English: is roughly 750 words.
With , the repeated start of each prompt is billed at the cheaper cache-read rate.
Gemini 3.8 Flash
- Input: 300M tokens @ $0.375/M
- $112.50
- Output: 60M tokens @ $1.875/M
- $112.50
- Total per month
- $225.00
Cost = tokens ÷ 1,000,000 × price per 1M, summed for input, cached input and output
Cheapest overall: Claude Haiku 5.5 at $30.00/month. Cheaper models can be weaker, so test them on your own prompts before switching.
This Workload on Every Model
300M input and 60M output tokens a month at batch prices where listed. Cheapest first; tap a model to load it above.
| Model | Tier | Input / 1M | Cached / 1M | Output / 1M | Context | Monthly cost | vs Gemini 3.8 Flash |
|---|---|---|---|---|---|---|---|
| Anthropic | Budget | $0.05 | $0.005 | $0.25 | 1M | $30.00 | -87% |
| OpenAI | Budget | $0.05 | $0.005 | $0.25 | 1.1M | $30.00 | -87% |
| DeepSeek | Budget | $0.112 | $0.0034 | $0.336 | 1M | $53.76 | -76% |
| Alibaba Qwen | Budget | $0.15 | $0.016 | $0.47 | 1M | $73.20 | -67% |
| Budget | $0.125 | $0.0125 | $0.75 | 1M | $82.50 | -63% | |
| Meta (open weights) | Budget | $0.35 | $0.17 | $1 | 524.3K | $165.00 | -27% |
| Mid | $0.375 | $0.0375 | $1.875 | 1M | $225.00 | selected | |
| DeepSeek | Mid | $0.103 | $0.098 | $4.11 | 1M | $277.50 | +23% |
| OpenAI | Mid | $0.5 | $0.025 | $2.5 | 1.1M | $300.00 | +33% |
| Mistral | Mid | $0.7 | $0.07 | $2.1 | 1M | $336.00 | +49% |
| Anthropic | Mid | $1 | $0.05 | $5 | 1M | $600.00 | +167% |
| Flagship | $1 | $0.05 | $5 | 1M | $600.00 | +167% | |
| OpenAI | Mid | $1 | $0.05 | $5 | 1.1M | $600.00 | +167% |
| xAI | Flagship | $1.6 | $0.4 | $4.8 | 500K | $768.00 | +241% |
| Anthropic | Flagship | $2 | $0.1 | $10 | 1M | $1,200.00 | +433% |
| Anthropic | Flagship | $5 | $0.125 | $25 | 1M | $3,000.00 | +1233% |
| OpenAI | Flagship | $5 | $0.5 | $25 | 1.1M | $3,000.00 | +1233% |
Prices are the per-token rates OpenRouter listed on 5 Nov 2026. Buying direct from a provider can be priced differently, and some providers charge more for very long prompts, so check the provider's pricing page before you commit a budget. Cache-write charges (paid the first time a prefix is cached) are not included; with a high cache share they add little. A month is 30 days.
Notes for This Preset
For bulk offline tasks (300,000 requests/month at 1,000 input and 200 output tokens), Google's Gemini 3.8 Flash on the Batch API costs $225.00/month ($0.75 per 1,000 requests) on OpenRouter (5 November 2026). Running the identical workload through real-time Gemini 3.8 Flash costs $495.00/month, so batch cuts the bill by about 55% in exchange for results arriving later instead of instantly. A cheaper model can cost far less for simple extraction: Claude Haiku 5.5 on Batch costs $30.00/month for the same workload, but test it on your own data first.
How can I lower the API bill for this workload?
Three levers, in order of effort: cache the repeated start of the prompt (system prompt, documents, tool definitions), move work that can wait to the Batch API, and test a cheaper model on your own prompts. Shorter answers help too, because output tokens cost several times more than input tokens.
Building an AI Chatbot, Agent or RAG App?
Vsurge Media builds production AI assistants, RAG search and automation for businesses, and helps keep the monthly API bill under control.