accounts/fireworks/models/gpt-oss-120b vs granite-4.0-h-micro
Input price
$0.15
$0.02
Output price
$0.60
$0.11
Context window
131K
131K
Throughput
118 tok/s
155 tok/s
Availability
98.0%
100.0%
Cost / task
$0.001
$0.000
Efficiency score
89
89
Estimated monthly cost by workload
Metric
ACCOUNTS
GRANITE-4.0-H-
Chat assistant
$117.00
$19.20
RAG / long context
$234.00
$33.90
Agent / tool use
$324.00
$54.00
Efficiency score: granite-4.0-h-micro
Across price, speed and reliability, granite-4.0-h-micro 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 accounts/fireworks/models/gpt-oss-120b or granite-4.0-h-micro cheaper?+
granite-4.0-h-micro has the lower input price — $0.02 vs $0.15 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, accounts/fireworks/models/gpt-oss-120b or granite-4.0-h-micro?+
Across price, speed and reliability, granite-4.0-h-micro offers the stronger overall balance for most workloads — but the right pick depends on your exact mix of input, output and latency needs.