GPT-5 mini
OpenAI · released 2026-01-15
Quality (AA Index)84
Input price$0.25
Output price$2.00
Context400K
Throughput280 tok/s
P50 latency0.3s
Side-by-side pricing, capabilities, real-world cost across common scenarios, and our editorial pick.
OpenAI · released 2026-01-15
Google · released 2025-09-01
链接通过我们的 OpenRouter 推荐链接在新标签页打开。 查看推广披露
| Metric | GPT-5 mini | Gemini 2.5 Pro | Verdict |
|---|---|---|---|
Input price /百万 tokens | $0.25 | $1.25 | GPT-5 mini −80% |
Output price /百万 tokens | $2.00 | $10.00 | GPT-5 mini −80% |
Context window max input length | 400K | 1M | Gemini 2.5 Pro +2.5× |
AA Quality AA Intelligence Index (0–100) | 84 | 87 | Gemini 2.5 Pro +3pt |
Arena Elo LMArena human-pref Elo (800–2000) | — | — | Tied |
Throughput tokens per second | 280 | 140 | GPT-5 mini +100% |
P50 latency first token | 0.3s | 0.8s | GPT-5 mini −63% |
Vision multimodal | Tied | ||
Function calling tool use | Tied | ||
Reasoning mode chain-of-thought | Tied |
| Scenario | GPT-5 mini | Gemini 2.5 Pro |
|---|---|---|
customer support 1000K req · 600/180 tok | $510 | $2.5K |
chat with docs 300K req · 4000/300 tok | $480 | $2.4K |
code generation 500K req · 2000/500 tok | $750 | $3.8K |
voice assistant 600K req · 800/200 tok | $360 | $1.8K |
GPT-5 family inheritance at a fraction of the cost — strong on routine tasks but visibly weaker on multi-step reasoning. Default choice when GPT-5 is overkill.
Set GPT-5 mini as primary, Gemini 2.5 Pro as fallback. One key, one bill, automatic failover when GPT-5 mini errors.
$ curl https://api.aipricly.com/v1/chat/completions \
-H "Authorization: Bearer $AIPC_KEY" \
-d '{
"routing": {
"primary": "openai/gpt-5-mini",
"fallback": ["google/gemini-2-5-pro"]
},
"messages": [{"role": "user", "content": "..."}]
}'