Gemini 3.8 Flash vs Gemini 2.5 Flash: API cost comparison
For a typical chatbot (1,500 input + 400 output tokens, 100,000 requests a month), Gemini 2.5 Flash is 45% cheaper: $147 vs $268 for Gemini 3.8 Flash. Paste your own prompt below to compare the exact cost of your workload.
0 characters0 words0 tokens (GPT o200k)
| Model | Per month |
|---|---|
| Gemini 3.8 Flash | |
| Gemini 2.5 Flash |
≈ = estimated token count: only OpenAI publishes its tokenizer. Claude counts use Anthropic’s published ratios; use the count_tokens API for an exact number.
Price per million tokens
USD, standard tier. Prices checked on October 28, 2026.
| Gemini 3.8 Flash | Gemini 2.5 Flash | |
|---|---|---|
| Input | $0.75 | $0.3 |
| Output | $3.75 | $2.5 |
| Cached input | $0.075 | $0.03 |
| Cache write (5 min) | Not charged separately | Not charged separately |
| Long prompts | Same price at any length | Same price at any length |
| Batch API | 50% off | 50% off |
| Provider | Google (Gemini) | Google (Gemini) |
Gemini 3.8 Flash: Price doubles in January 2027 ($1.50 / $7.50).
Monthly cost for common workloads
| Workload | Gemini 3.8 Flash | Gemini 2.5 Flash |
|---|---|---|
| Chatbot 1,500 input + 400 output tokens, 100,000 requests a month | $268 | $147 |
| Document Q&A (RAG) 8,000 input + 500 output tokens, half the input cached, 20,000 requests a month | $107 | $52.72 |
| Long-document summary 150,000 input + 2,000 output tokens, 1,000 requests a month | $126 | $52.25 |
| Bulk classification (Batch API) 500 input + 20 output tokens, 1 million requests a month, Batch API where available | $234 | $104 |
Token counts are converted per model: the same text becomes a different number of tokens on each provider (see below). The cheaper option in each row is highlighted.
Frequently asked questions
Is Gemini 3.8 Flash cheaper than Gemini 2.5 Flash?
Per million tokens, Gemini 3.8 Flash costs $0.75 / $3.75 (input / output) and Gemini 2.5 Flash costs $0.3 / $2.5. For a typical chatbot workload (1,500 input + 400 output tokens, 100,000 requests a month), Gemini 2.5 Flash is 45% cheaper: $147 vs $268 for Gemini 3.8 Flash. Token counts differ between providers, so compare the cost of the same prompt rather than the price per token.
How much do Gemini 3.8 Flash and Gemini 2.5 Flash cost per million tokens?
Gemini 3.8 Flash: $0.75 / $3.75 for input / output, $0.075 for cached input. Gemini 2.5 Flash: $0.3 / $2.5, $0.03 for cached input. Prices in US dollars, standard tier, checked on October 28, 2026.
Do Gemini 3.8 Flash and Gemini 2.5 Flash count tokens the same way?
Gemini 3.8 Flash's tokenizer is not published. We estimate about 1.05× the GPT o200k count for the same text. Gemini 2.5 Flash's tokenizer is not published. We estimate about 1.05× the GPT o200k count for the same text.
Do Gemini 3.8 Flash and Gemini 2.5 Flash have a Batch API discount?
Both do: Gemini 3.8 Flash gets 50% off and Gemini 2.5 Flash 50% off for requests sent through the Batch API, which may take up to 24 hours.
Related comparisons
- Claude Haiku 5.5 vs Gemini 3.8 Flash
- GPT-6.1 Terra vs Gemini 3.8 Flash
- Gemini 3.8 Flash vs DeepSeek Flash