GPT OSS 120B
GPT OSS 120BAlternatives?
BetterMiMo v2.6 ProthinkingOpen+4.8+806%$0.13Memory (4-bit): 70 GB → 615 GB+4
OpenQwen3.8 27Bunstated+2.5+1,494%$0.42 / $2.55max_tokens range · QwenCloud+4BetterGPT-5.6 Solhigh+5.4+13,233%$0.81
BetterGemini 3.8 Flashhigh+3.3+2,400%*$1.24Sampling parameters are ignored+1
BetterGLM 5.2maxOpen+3.6+3,483%$1.47Memory (4-bit): 70 GB → 452 GBMiMo v2.6 ProthinkingOpen+4.8+806%$0.13Memory (4-bit): 70 GB → 615 GB+4GPT-5.6 Solhigh+5.4+13,233%$0.81Gemini 3.8 Flashhigh+3.3+2,400%*$1.24Sampling parameters are ignored+1GLM 5.2maxOpen+3.6+3,483%$1.47Memory (4-bit): 70 GB → 452 GBGPT-6 Astrahigh+6.6+33,233%$1.73Monitoring can return HTTP 403+2Qwen3.8 27BunstatedOpen+2.5+1,494%$0.42 / $2.55max_tokens range · QwenCloud+4Gemma 4 31BunstatedOpen+1.3+167%$0.10 / $0.34
Mistral Medium 3.5unstatedOpensame+4,900%$1.50 / $7.50Memory (4-bit): 70 GB → 77 GB
MiniMax M2.7unstatedOpensame+775%$0.30 / $1.20Memory (4-bit): 70 GB → 137 GBGPT-6 Astrahigh+6.6—$1.73Monitoring can return HTTP 403+2GPT-5.6 Solxhigh+5.6—$1.18GPT-5.5xhigh+5.6—$2.63Prompts with >272K input tokensGPT-5.4medium+5.1—$2.50 / $15GPT-5.2medium+3.5—$1.75 / $14GPT-6.1 Solmediumn/a—$0.21Remove unsupported parameters+5GPT-6 Lunamediumn/a—$0.017Function calling only with none · Chat Completions+3GPT-6 Solmediumn/a—$0.25All OpenAI models →Run it yourself
estimateBenchmarks
in Writing & LanguageFAQ
How much does GPT OSS 120B cost?›
$0.03 per 1M input tokens and $0.15 per 1M output tokens (cheapest host: Near AI).
Is GPT OSS 120B free to use?›
There is no free API; the cheapest paid price is $0.03 per 1M input tokens. The weights are open, so you can run it yourself.
How good is GPT OSS 120B, and what is it best at?›
#251 of 334 in Chat & Knowledge, #75 of 132 in Coding, #130 of 133 in Agents & Tool Use, #144 of 195 in Writing & Language, #91 of 133 in Vision & Documents.
Is GPT OSS 120B better than Grok 4.6?›
On Lech Mazur Short-Story, GPT OSS 120B scores -3.2 vs -2.9 — about the same.
How can I use GPT OSS 120B?›
Through the API of AWS Bedrock, AkashML, Amazon Bedrock, Azure AI Foundry, BaseTen and 18 more.
What is the context window of GPT OSS 120B?›
131K tokens.
When was GPT OSS 120B released? Is there a newer version?›
Released 2025-08-05. It is the current version in its line.
Is GPT OSS 120B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run GPT OSS 120B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can GPT OSS 120B read images?›
No, it accepts text only.
What is GPT OSS 120B?›
GPT OSS 120B is an open-weights language model from OpenAI, released Aug 2025.
What are the best alternatives to GPT OSS 120B?›
MiMo v2.6 Pro (better), Qwen3.8 27B (open weights).