AI Model Comparison

GPT OSS 120B compared to other AI models

Compare GPT OSS 120B from OpenAI on pricing, benchmarks, zero data retention, EU hosting, providers, and context. Add another model to start a side-by-side.

Key info

What each model gives you per call. Prices reflect the cheapest available route on Opper.

Input
Output
Features
Context window
128Ktokens
Max output
8Ktokens
Input price
$0.04/ 1M tokens
Output price
$0.18/ 1M tokens

Benchmarks

Composite indices and speed metrics from Artificial Analysis. Higher is better for indices and speed (averaged across providers); lower is better for time-to-first-token.

Intelligence Index
Coding Index
30
Math Index
93
Output speed
221 t/s
Time to first token
545ms

Available routes & privacy

Every provider hosting this model on Opper. Routes are sorted best-privacy first, so EU regions and zero data retention rise to the top.

RoutesProvider, region, ZDR & training posture.
AWS Bedrock
RegionEU
ZDR
TrainingNo
evroc
RegionEU
ZDR
TrainingNo
Geodd
RegionEU
ZDR
TrainingNo
GreenPT
RegionEU
ZDR
TrainingNo
Infercom
RegionEU
ZDR
TrainingNo
Regolo
RegionEU
ZDR
TrainingNo
Fireworks
RegionMulti
ZDR
TrainingNo
SCX
RegionMulti
ZDR
TrainingNo
Cerebras
RegionUS
ZDR
TrainingNo
Geodd
RegionUS
ZDR
TrainingNo
Groq
RegionUS
ZDR
TrainingNo
Novita
RegionUS
ZDR
TrainingNo
Scaleway
RegionEU
ZDR
TrainingNo
BytePlus
RegionMulti
ZDR
TrainingNo
DigitalOcean
RegionUS
ZDR
TrainingNo
Nebius
RegionMulti
ZDR
TrainingNo

Popular comparisons

Pick a row, or use the picker above to build your own.

Comparing families rather than specific models? Start from a brand comparison:

Or browse overall benchmark rankings on the LLM leaderboard.

One API key, every model you compared

EU-hosted, zero data retention on supported routes, pass-through pricing. Drop-in OpenAI SDK compatible — switch between models without changing your code.