GPT-4o Mini is still available, but OpenAI has released newer models. Details
Cost Comparison
| Prompts | GPT-4o Mini | Gemini 3.8 Flash |
|---|---|---|
| 1 | $0.000375 | $0.0022 |
| 100 | $0.0375 | $0.2250 |
| 1,000 | $0.3750 | $2.25 |
| 10,000 | $3.75 | $22.50 |
| 100,000 | $37.50 | $225.00 |
Based on 500 input + 500 output tokens per prompt. Prices verified October 2026. Embed this calculator
At 10,000 requests per day, GPT-4o Mini costs $112.50/month vs Gemini 3.8 Flash at $675.00/month — GPT-4o Mini is 83% cheaper.
| GPT-4o Mini | Gemini 3.8 Flash | |
|---|---|---|
| Input price | $0.15 / 1M | $0.75 / 1M |
| Output price | $0.60 / 1M | $3.75 / 1M |
| Cached input | $0.075 / 1M | $0.075 / 1M |
| Typical prompt | $0.000375 | $0.0022 |
| Batch discount | 50% off | 50% off |
| Context window | 128K tokens | 1M tokens |
| Max output | 16,384 tokens | 65,536 tokens |
| Knowledge cutoff | Oct 2023 | Mar 2026 |
| Input types | Text, Images, PDF | Text, Images, Video, Audio, PDF |
| Reasoning mode | No | Always on |
| Open weights | No | No |
| Released | July 18, 2024 | September 2, 2026 |
| Status | Older, still available | Current |
Try It Yourself
How many tokens you expect the model to generate per response
Showing a typical prompt (500 input + 500 output tokens) across 27 models. Paste your own prompt above for an exact count.
| Model | Per Prompt | Prompts / $1 | Monthly |
|---|---|---|---|
GPT-4o MiniOlder OpenAI | $0.0003750.037¢ | 2,666 | $1.13 |
| $0.00220.22¢ | 444 | $6.75 | |
GPT-6 LunaCheapest OpenAI | $0.0003000.03¢ | 3,333 | $0.9000 |
| Mistral | $0.0003750.037¢ | 2,666 | $1.13 |
| OpenAI (via Together) | $0.0003750.037¢ | 2,666 | $1.13 |
| OpenAI | $0.0007000.07¢ | 1,428 | $2.10 |
| DeepSeek | $0.0007500.075¢ | 1,333 | $2.25 |
| Meta (via Together) | $0.0009250.092¢ | 1,081 | $2.77 |
| Mistral | $0.00100.1¢ | 1,000 | $3.00 |
| $0.00140.14¢ | 714 | $4.20 | |
| xAI | $0.00190.19¢ | 533 | $5.63 |
| DeepSeek | $0.00260.26¢ | 378 | $7.92 |
| Meta | $0.00270.27¢ | 363 | $8.25 |
| Anthropic | $0.00300.3¢ | 333 | $9.00 |
| xAI | $0.00400.4¢ | 250 | $12.00 |
| Alibaba (Qwen) | $0.00400.4¢ | 250 | $12.00 |
| Mistral | $0.00450.45¢ | 222 | $13.50 |
| OpenAI | $0.00600.6¢ | 166 | $18.00 |
| OpenAI | $0.00600.6¢ | 166 | $18.00 |
| Anthropic | $0.00600.6¢ | 166 | $18.00 |
| OpenAI | $0.00700.7¢ | 142 | $21.00 |
| $0.00700.7¢ | 142 | $21.00 | |
| Moonshot AI | $0.00900.9¢ | 111 | $27.00 |
| OpenAI | $0.0120 | 83 | $36.00 |
| Anthropic | $0.0120 | 83 | $36.00 |
| OpenAI | $0.0300 | 33 | $90.00 |
| Anthropic | $0.0300 | 33 | $90.00 |
Prices from official provider pricing pages, verified October 2026.
GPT-4o Mini vs Gemini 3.8 Flash — Frequently Asked Questions
GPT-4o Mini is 83% cheaper than Gemini 3.8 Flash. One typical prompt (500 input + 500 output tokens) costs $0.000375 on GPT-4o Mini and $0.0022 on Gemini 3.8 Flash. GPT-4o Mini charges $0.15/$0.60 per million tokens (input/output) vs Gemini 3.8 Flash's $0.75/$3.75.
It depends on your priorities. GPT-4o Mini is more cost-effective at $0.3750 per 1,000 prompts. Gemini 3.8 Flash may offer different capabilities or quality. GPT-4o Mini has a 128K context window vs Gemini 3.8 Flash's 1M. Use the calculator above to compare at your actual volume.
Beyond price: GPT-4o Mini accepts text, images and PDFs, writes up to 16,384 tokens per response, has a knowledge cutoff of October 2023 and has no reasoning mode. Gemini 3.8 Flash accepts text, images, video, audio and PDFs, writes up to 65,536 tokens per response, has a knowledge cutoff of March 2026 and always reasons before answering. GPT-4o Mini has a 128K context window and Gemini 3.8 Flash 1M. See the specs table above for a side-by-side view.
At 10,000 requests per day, switching from Gemini 3.8 Flash to GPT-4o Mini saves about $562.50/month — a 83% cut on every call. Savings scale linearly with volume.
At 100,000 daily requests, GPT-4o Mini costs $1,125.00/month and Gemini 3.8 Flash costs $6,750.00/month — a difference of $5,625.00/month.