gpt-4-0613 vs gpt-4-turbo-preview
Input price
$30.00
$10.00
Output price
$60.00
$30.00
Context window
8K
128K
Throughput
149 tok/s
148 tok/s
Availability
99.5%
99.1%
Cost / task
$0.090
$0.035
Efficiency score
74
75
Estimated monthly cost by workload
Metric
GPT-4-0613
GPT-4-TURBO-PR
Chat assistant
$16,200
$6,600
RAG / long context
$41,400
$14,700
Agent / tool use
$43,200
$18,000
Efficiency score: gpt-4-turbo-preview
Across price, speed and reliability, gpt-4-turbo-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 gpt-4-0613 or gpt-4-turbo-preview cheaper?+
gpt-4-turbo-preview has the lower input price — $10.00 vs $30.00 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, gpt-4-0613 or gpt-4-turbo-preview?+
Across price, speed and reliability, gpt-4-turbo-preview offers the stronger overall balance for most workloads — but the right pick depends on your exact mix of input, output and latency needs.