Gemini 2.5 Flash vs GPT-5 Mini
Cost and capability comparison. For a sample workload of 1,000 input and 500 output tokens across 100,000 requests/month, GPT-5 Mini is cheaper by about $30.00/month.
| Gemini 2.5 Flash | GPT-5 Mini | |
|---|---|---|
| Intelligence | ||
| Arena · Overall(LMArena Elo — higher is better) | 1417✓ | 1373 |
| Arena rank (overall) | #61✓ | #85 |
| Arena · Coding | 1370 | 1388✓ |
| Arena · Math & reasoning | 1385 | 1390✓ |
| Arena · Agentic / tool use | 1368 | 1378✓ |
| Score evidence | Measured | Measured |
| Pricing (USD / 1M tokens) | ||
| Input | $0.3000 | $0.2500✓ |
| Output | $2.50 | $2.00✓ |
| Cached input (read) | $0.0300 | $0.0250✓ |
| Cache write | — | — |
| Blended(3:1 input:output blend) | $0.8500 | $0.6875✓ |
| Specs & capabilities | ||
| Provider | OpenAI | |
| Context window | 1M (1,000,000)✓ | 128K (128,000) |
| Max output | 65,536✓ | 64,000 |
| Modalities | text, image, audio, video | text, image |
| Vision | Yes | Yes |
| Tool use | Yes | Yes |
| Reasoning | Yes | Yes |
| Prompt caching | Yes | Yes |
| Batch pricing | Yes | Yes |
| Tokenizer | gemini | o200k_base |
| Release date | — | — |
| Status | ga | ga |
Intelligence scores are community Arena ratings from LMArena / arena.ai, used under CC BY 4.0. Snapshot last refreshed 27 August 2026. Scores are a relative signal, not an absolute measure of capability. A Measured score was voted on directly; an Estimated score is inherited from an identical base model (a regional/creator-prefixed hosting duplicate). See our methodology.
Compare on your own workload
Gemini 2.5 Flash and GPT-5 Mini are pre-loaded. Adjust the tokens and monthly volume to see which is cheaper for your usage.
Used unless you set active users below.
Results update automatically as you type.
| GPT-5 Mini | OpenAI | $0.00125 | $125.00 | $1,500.00 | 128,000 |
| Gemini 2.5 Flash | $0.00155 | $155.00 | $1,860.00 | 1,000,000 |
FAQ
Which is cheaper, Gemini 2.5 Flash or GPT-5 Mini?
For a workload of 1,000 input and 500 output tokens over 100,000 requests/month, GPT-5 Mini is cheaper, costing about $125.00/month versus $155.00/month.
What is the context window of Gemini 2.5 Flash and GPT-5 Mini?
Gemini 2.5 Flash supports 1,000,000 tokens, while GPT-5 Mini supports 128,000 tokens.
Estimates for planning only. Verify current pricing with each provider.