@cf/openai/gpt-oss-120b vs granite-4.0-h-micro
Lower price
@cf/openai/gpt-oss-120b
Faster
@cf/openai/gpt-oss-120b
Higher efficiency
@cf/openai/gpt-oss-120b
Input price
$0.00
$0.02
Output price
$0.00
$0.11
Context window
128K
131K
Throughput
168 tok/s
155 tok/s
Availability
99.8%
100.0%
Cost / task
$0.000
$0.000
Efficiency score
89
89
Estimated monthly cost by workload
Metric
-CF
GRANITE-4.0-H-
Chat assistant
$0.00
$19.20
RAG / long context
$0.00
$33.90
Agent / tool use
$0.00
$54.00
Efficiency score: @cf/openai/gpt-oss-120b
Across price, speed and reliability, @cf/openai/gpt-oss-120b 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 @cf/openai/gpt-oss-120b or granite-4.0-h-micro cheaper?+
@cf/openai/gpt-oss-120b has the lower input price — $0.00 vs $0.02 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, @cf/openai/gpt-oss-120b or granite-4.0-h-micro?+
Across price, speed and reliability, @cf/openai/gpt-oss-120b offers the stronger overall balance for most workloads — but the right pick depends on your exact mix of input, output and latency needs.