Gemini 2.5 Pro token cost & pricing
Gemini 2.5 Pro pairs a 1M-token context window with strong multimodal understanding, making it the standard choice for whole-codebase analysis, hour-long video processing and very large document sets. It is the only frontier-tier model here where filling the context window is a realistic workflow rather than an edge case.
Gemini 2.5 Pro specifications
| Vendor | |
|---|---|
| Input price | $1.25 / 1M tokens |
| Output price | $10 / 1M tokens |
| Cached input price | $0.31 / 1M tokens (75% cheaper) |
| Context window | 1,048,576 tokens |
| Max output | 65,536 tokens |
| Open weights | No |
| Price rank | 13 of 17 (cheapest first) |
| Best for | long-context, multimodal |
What Gemini 2.5 Pro costs in practice
Four common workloads, priced at list rates. Monthly figures assume 30 days.
| Workload | Per request | Requests/day | Per month |
|---|---|---|---|
| Chatbot · 1K in / 500 out | $0.0063 | 10,000 | $1,875 |
| RAG Q&A · 8K in / 400 out | $0.01 | 5,000 | $2,100 |
| Doc summary · 30K in / 1K out | $0.05 | 1,000 | $1,425 |
| Code agent · 60K in / 3K out | $0.10 | 500 | $1,575 |
How many requests does $100 buy?
Assuming a 1,000-token prompt and a 500-token response per request.
How Gemini 2.5 Pro pricing actually works
At $1.25 per million input and $10 per million output, Gemini 2.5 Pro undercuts Claude Sonnet 4.5 by more than half on input. Cached input is $0.31 per million. The catch is that a genuinely full 1M-token call costs $1.25 in input alone, so long-context usage must be deliberate.
When to use Gemini 2.5 Pro
Reach for it when the task requires seeing everything at once: auditing a repository, comparing dozens of contracts, reasoning over a full meeting transcript plus slides. For short prompts it offers no advantage over cheaper models.
How to cut your Gemini 2.5 Pro bill
Chunk and prefilter before sending. Retrieval over 1M tokens is still retrieval — sending 800K tokens of mostly irrelevant context costs 800x more than a targeted 1K-token prompt. Use the long window for what genuinely needs global context.
Other Google models
Cheaper alternatives to Gemini 2.5 Pro
- Mistral Large 2Mistral29% cheaper
- Qwen3 MaxAlibaba36% cheaper
- Claude Haiku 4.5Anthropic47% cheaper
- Kimi K2Moonshot72% cheaper
Run the numbers on your own prompt
Paste your actual text into the token counter to get an exact count instead of an estimate. Nothing is uploaded.
Open the calculator →