Skip to contentx402 is live on Robinhood Chain: agents can now pay for any model, per call, in USDG →
OmniRail
← All models

OpenAI · Language model

gpt-oss-120b

openai/gpt-oss-120b
  • Language
Released Aug 5, 2025

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}'