GPT-5
OpenAI · released 2026-01-15
Quality (AA Index)91
Input price$1.25
Output price$10.00
Context400K
Throughput120 tok/s
P50 latency0.7s
GPT-5 vs GPT-5 mini
Side-by-side pricing, capabilities, real-world cost across common scenarios, and our editorial pick.
Add a modelUp to 4 models can be compared
all prices in USD per 1M tokens
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
Links open in a new tab via our OpenRouter referral. Affiliate disclosure
Head-to-head specs
Green column = winner per metric| Metric | GPT-5 | GPT-5 mini | Verdict |
|---|---|---|---|
Input price /1M tokens | $1.25 | $0.25 | GPT-5 mini −80% |
Output price /1M tokens | $10.00 | $2.00 | GPT-5 mini −80% |
Context window max input length | 400K | 400K | Tied |
AA Quality AA Intelligence Index (0–100) | 91 | 84 | GPT-5 +7pt |
Arena Elo LMArena human-pref Elo (800–2000) | — | — | Tied |
Throughput tokens per second | 120 | 280 | GPT-5 mini +133% |
P50 latency first token | 0.7s | 0.3s | GPT-5 mini −57% |
Vision multimodal | Tied | ||
Function calling tool use | Tied | ||
Reasoning mode chain-of-thought | Tied |
Monthly cost across common scenarios
Default usage assumptions| Scenario | GPT-5 | GPT-5 mini |
|---|---|---|
customer support 1000K req · 600/180 tok | $2.5K | $510 |
chat with docs 300K req · 4000/300 tok | $2.4K | $480 |
code generation 500K req · 2000/500 tok | $3.8K | $750 |
voice assistant 600K req · 800/200 tok | $1.8K | $360 |
Our pick
For most workloads, choose GPT-5 mini.
- 80% cheaper input price, which compounds at scale
- 133% faster throughput — matters for streaming UX and voice agents
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.
Choose GPT-5 instead if: Best across-the-board quality but the most expensive token rate in the table; pick GPT-5 when reasoning depth or function-calling reliability outranks per-million-token spend.
Read our deep analysis
Why pick? Use both with smart routing
Phase 2 · gateway with fallback chainSet GPT-5 mini as primary, GPT-5 as fallback. One key, one bill, automatic failover when GPT-5 mini errors.
PHASE 2 PREVIEW · gateway not live yetThis endpoint does not exist yet. The gateway is in Phase 2 — what you see below is a design preview of the planned interface, not a live API. We will email subscribers when it launches.
Preview the planned API call
$ curl https://api.aipricly.com/v1/chat/completions \
-H "Authorization: Bearer $AIPC_KEY" \
-d '{
"routing": {
"primary": "openai/gpt-5-mini",
"fallback": ["openai/gpt-5"]
},
"messages": [{"role": "user", "content": "..."}]
}'