Google: Gemini 2.5 Flash vs OpenAI: GPT-4.1 Mini
On input price, Google: Gemini 2.5 Flash is ~1.3× cheaper. Verified 2026-10-21.
Google: Gemini 2.5 Flash $0.300/$2.50vsOpenAI: GPT-4.1 Mini $0.400/$1.60
Verdict
On blended price (3:1 input:output), OpenAI: GPT-4.1 Mini is ~1.2× cheaper ($0.400/$1.60 vs $0.300/$2.50 per 1M tokens).
Pricing
Per-million-token list prices, verified 2026-10-21. Green marks the better value.
| Metric | Google: Gemini 2.5 Flash | OpenAI: GPT-4.1 Mini |
|---|---|---|
| Input / 1M | $0.300 | $0.400 |
| Output / 1M | $2.50 | $1.60 |
| Cache read / 1M | $0.030 | $0.100 |
| Blended (3:1) | $0.850/1M | $0.700/1M |
| Estimated monthly cost | Google: Gemini 2.5 Flash | OpenAI: GPT-4.1 Mini |
|---|---|---|
| Chatbot10,000 reqs · 800/400 tok | $12.40 | $9.60 |
| Coding agent5,000 reqs · 8000/2000 tok | $37.00 | $32.00 |
| RAG pipeline30,000 reqs · 4000/500 tok | $73.50 | $72.00 |
Plug in your own numbers in the calculator, or paste a real bill into the Bill Shredder.
Specifications & capabilities
| Metric | Google: Gemini 2.5 Flash | OpenAI: GPT-4.1 Mini |
|---|---|---|
| Context window | 1.0M | 1.0M |
| Max output | 66K | 33K |
| Vision input | ✓ | ✓ |
| Tool calling | ✓ | ✓ |
| Reasoning | ✓ | – |
Performance
Measured by Artificial Analysis on live endpoints.
Speed measurements aren't available for both models yet.
Provider
Infrastructure metrics for the organizations behind these models.
| Metric | OpenAI | |
|---|---|---|
| Listed endpoints | 15 | 12 |
| Reliability | 99.7% | 99.9% |
| Avg latency | 380 ms | 450 ms |
| Pricing tiers | standard, batch | standard, batch, provisioned |
Full details: Google: Gemini 2.5 Flash pricing · OpenAI: GPT-4.1 Mini pricing