Model scorecard
OpenAI gpt-5.5
Composite 64.6/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.
B+64.6/100openai/gpt-5.5text · vision · audio · 400k context
Capability
eval compositeQuality (blended eval)94
Category: reasoning
Usable context20
400k advertised window
Serving
gateway measuredThroughput21
74 output tokens/s median
Time to first token32
410ms p50
Economics
at provider costPrice efficiency52
$12.50 per 1M output tokens
Quality per dollar23
llmcloud adds $0 to these token prices.
Suggested usage
- Deep reasoning & mathauto:reasoning
Reasoning tokens dominate the bill, so quality per thinking-token beats headline price.
- Long-context retrievalauto:long-context
Effective recall at depth, not the advertised window, is the deciding number.
- Vision & document parsingauto:vision
Chart and table extraction quality separates models far more than natural-image captioning.