← All models
OpenAI · Language model
gpt-oss-120b
openai/gpt-oss-120b- Language
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...
Specifications
- Context window
- 131,072 tokens
- Max output
- 65,536 tokens
- Input
- text
- Output
- text
- Reasoning effort
- high, medium, low (always on)
- Tokenizer
- GPT
- Knowledge cutoff
- 2024-06-30
Supported parameters
Accepted by the model and forwarded as-is by the gateway.
- frequency_penalty
- logit_bias
- logprobs
- max_tokens
- min_p
- presence_penalty
- reasoning
- reasoning_effort
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_a
- top_k
- top_logprobs
- top_p
Use it
POST /api/v1/chat/completions · MCP chat · full reference
curl https://omnirail.org/api/v1/chat/completions \
-H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
-d '{"model":"openai/gpt-oss-120b","messages":[{"role":"user","content":"Hello"}],"max_tokens":300}'