All models
Head to head
GPT-OSS 120B vs DeepSeek V3.1
Price, context, inputs and filters. No benchmarks theatre.
GPT-OSS 120B costs 1.7× less per message.
DeepSeek V3.1 holds 1.3× more context.
Made by
OpenAI
DeepSeek
Content tier
Open
Open
Intelligence
Smart & Cheap
Smart & Cheap
Estimated price per message
~0.43 credits≈ 232 messages for $1
~0.71 credits≈ 140 messages for $1
Context window
131K tokens≈ 202 pages of text in one go
164K tokens≈ 252 pages of text in one go
Reads
Text
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
Legacy
A typical message: 16K tokens in, 1.5K out. Short replies cost less. Models served via OpenRouter bill the real provider cost plus our markup, so actual charges vary. 1 credit = $0.01.