Head-to-Head Pricing Benchmark
Side-by-side pricing and context window comparison for production model selection.
Default Recommendation (120M input + 60M output)
Google: Gemini 3.1 Flash Lite Preview is lower-cost for the default monthly workload scenario.
Adjust the workload in the calculator below to see a live recommendation for your usage.
| Metric | OpenAI: GPT-5.1-Codex-Mini | Google: Gemini 3.1 Flash Lite Preview |
|---|---|---|
| Developer | openai | |
| Context Window | 400,000 | 1,048,576 |
| Max Output Tokens | 128,000 | 65,536 |
| Input Cost / 1M Tokens | $0.2500 | $0.2500 |
| Output Cost / 1M Tokens | $2.00 | $1.50 |
| Projected Monthly Cost | $150 | $120 |
| Vision | ✅ Yes | ✅ Yes |
| Tool Calling | ✅ Yes | ✅ Yes |
| Structured Output | ✅ Yes | ✅ Yes |
| Reasoning | ✅ Yes | ✅ Yes |
| Web Search | ❌ No | ❌ No |
| Audio Price / 1M | N/A | $0.5000 |
| Tokenizer | GPT | Gemini |
| MMLU Score | 82.0 | N/A |
| GPQA | 81.3 | N/A |
Price History
Current Input / 1M
$0.2500
Current Output / 1M
$2.00
Price History
Current Input / 1M
$0.2500
Current Output / 1M
$1.50
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
99.7%
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
99.3%
Adjust your workload to see projected monthly costs.
OpenAI: GPT-5.1-Codex-Mini
$150
per month
Google: Gemini 3.1 Flash Lite Preview
$120
per month
Lower costLive Recommendation
Google: Gemini 3.1 Flash Lite Preview is lower-cost at 120M input + 60M output tokens/month.
Continue evaluation with more “A vs B pricing” decision pages.