All models
Head to head
Qwen 3.8 Flash vs GPT-OSS 120B
Price, context, inputs and filters. No benchmarks theatre.
Both cost about the same per message.
Qwen 3.8 Flash holds 7.6× more context.
Made by
Alibaba
OpenAI
Content tier
Open
Open
Intelligence
Smart & Cheap
Smart & Cheap
Price per message
~0.41 credits≈ 243 messages for $1
~0.43 credits≈ 232 messages for $1
Context window
1M tokens≈ 1,538 pages of text in one go
131K tokens≈ 202 pages of text in one go
Reads
Text, Images, Video
Text
Writes
Text
Text
Tool use
Yes - search, memory, code and more
Yes - search, memory, code and more
Served via
OpenRouter, Unbottled AI
OpenRouter, Unbottled AI
Status
Current
Current
A typical message: 16K tokens in, 1.5K out. Short replies cost less. 1 credit = $0.01.