AI Model Comparison

GPT OSS 120B vs Gemini 3.5 Flash

Compare on pricing, benchmarks, zero data retention, EU hosting, providers, and context.

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
$0.05/ 1M tokens
Output price
$0.25/ 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
29
Math Index
93
Output speed
336 t/s
Time to first token
523ms

Available routes & privacy

Every provider hosting this model on Opper. Routes are sorted best-privacy first — EU regions and self-serve ZDR rise to the top.

RoutesProvider, region, ZDR & training posture.
AWS Bedrock
RegionEU
ZDRAlways-on
TrainingNo
Berget
RegionEU
ZDRAlways-on
TrainingNo
Evroc
RegionEU
ZDRAlways-on
TrainingNo
Infercom
RegionEU
ZDRAlways-on
TrainingNo
Nebius
RegionEU
ZDREnterprise
TrainingNo
Cerebras
RegionUS
ZDREnterprise
TrainingNo
Fireworks
RegionUS
ZDREnterprise
TrainingNo
Groq
RegionUS
ZDREnterprise
TrainingNo
Novita
RegionUS
ZDREnterprise
TrainingNo

One API key, every model you compared

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

GPT OSS 120B vs Gemini 3.5 Flash — compare AI models side by side | Opper AI