Benchmarks

OpenAI: gpt-oss-120b (free)

openai/gpt-oss-120b:free

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

Prompt $/1M
free
Completion $/1M
free
Context
131,072 tok
Best provider
13 tok/s · OpenInference

Specs

Model id
openai/gpt-oss-120b:free
Display name
OpenAI: gpt-oss-120b (free)
Modality
text->text
Tokenizer
GPT
Instruct type
Context length
131,072
Max completion
131,072
Prompt $/1M
free
Completion $/1M
free
Free tier
yes

Capabilities

  • Function callingno
  • JSON modeno
  • System promptno
  • Visionno
  • Moderatedyes

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Providertok/s
OpenInferencefastest13
openaifastest
OpenAI: gpt-oss-120b (free) - Benchmarks, Pricing and Speed | TryAii