goliath-120b vs gpt-4o-search-preview
Input price
$3.75
$2.50
Output price
$7.50
$10.00
Context window
6K
128K
Throughput
158 tok/s
145 tok/s
Availability
99.3%
96.7%
Cost / task
$0.011
$0.010
Efficiency score
85
85
Estimated monthly cost by workload
Metric
GOLIATH-120B
GPT-4O-SEARCH-
Chat assistant
$2,025
$1,950
RAG / long context
$5,175
$3,900
Agent / tool use
$5,400
$5,400
Efficiency score: gpt-4o-search-preview
Across price, speed and reliability, gpt-4o-search-preview offers the stronger overall balance for most workloads — but the right pick depends on your exact mix of input, output and latency needs.
Figures are illustrative demo data, not financial advice.
Frequently asked questions
Is goliath-120b or gpt-4o-search-preview cheaper?+
gpt-4o-search-preview has the lower input price — $2.50 vs $3.75 per 1M tokens — so for most blended workloads it is the more cost-effective of the two. Figures are illustrative demo data.
Which should I choose, goliath-120b or gpt-4o-search-preview?+
Across price, speed and reliability, gpt-4o-search-preview offers the stronger overall balance for most workloads — but the right pick depends on your exact mix of input, output and latency needs.