GPT OSS 120B vs Qwen3.8 27B

Cheapest prices, context length and providers, side by side.

GPT OSS 120B

by OpenAI

Qwen3.8 27B

by Alibaba

Overview

Creator
Type
LLM
LLM
Context length
131k
992k ●
Max output
—
128k
Open weights
Yes
Yes
Parameters
117B MoE (5.1B active)
—
Capabilities
Function callingJSON modeStreaming
VisionFunction callingJSON modeStreaming
Categories
Chat / InstructCode
Chat / Instruct
Providers
19
19

Pricing

Cheapest input / 1m tokens
$0.030 ●
OpenRouter
$0.040
OpenRouter
Cheapest output / 1m tokens
$0.150 ●
OpenRouter
$1.35
OpenRouter

Cheapest available offer. Prices in USD. ● marks the better value.

Cheapest providers

GPT OSS 120B
OpenRouter
$0.030/1M in · $0.150/1M out
Visit
DeepInfra
$0.037/1M in · $0.170/1M out
Visit
Infron
$0.037/1M in · $0.170/1M out
Visit
AK
AkashML
$0.037/1M in · $0.187/1M out
Visit
Runcrate
$0.041/1M in · $0.187/1M out
Visit
See all 19 providers →
Qwen3.8 27B
OpenRouter
$0.040/1M in · $1.35/1M out
Visit
Runcrate
$0.165/1M in · $2.07/1M out
Visit
DeepInfra
$0.200/1M in · $2.50/1M out
Visit
AK
AkashML
$0.225/1M in · $1.98/1M out
Visit
Parasail
$0.240/1M in · $2.20/1M out
Visit
See all 19 providers →

More comparisons

Subscribe to our newsletter

News and updates, 1–2 emails per month. No spam.