chooseaimodel
← Compare models

GPT-5.4 Mini vs Mercury 2

List-price comparison ·GPT-5.4 Mini details ·Mercury 2 details

ShareXFacebookLinkedIn

For a typical workload (100,000 requests / mo), Mercury 2 is the cheapest — 78% less than the priciest here ($60.00/mo vs $270.00/mo).

 GPT-5.4 MiniMercury 2
Input / 1M tokens$0.750$0.250
Output / 1M tokens$4.50$0.750
Typical request (1,200 in + 400 out)$0.0027$0.0006
Context window400k tokens128k tokens
Max output128k tokens50k tokens
Quality score80/10068/100
TierBalancedBalanced
ProviderOpenAIInception

Projected monthly cost

Requests / moGPT-5.4 MiniMercury 2
1,000$2.70$0.6
10,000$27.00$6.00
100,000$270.00$60.00
Open all in the calculator — adjust volume and token counts →

GPT-5.4 Mini

Good default for everyday chat, summarization, and lightweight agent steps where GPT-5.4-level reasoning isn't required.

Quality gap widens on long, multi-hop reasoning tasks — needs careful prompt design to avoid silent failures on edge cases.

Mercury 2

Auto-synced from OpenRouter — no editorial write-up yet.

More comparisons

Vendor list rates · per-request examples assume 1,200 input + 400 output tokens.