OpenAI / openai/gpt-oss-120b-unmetered

GPT-OSS 120B - access through LLMTR

GPT-OSS 120B is OpenAI's open-weight Mixture-of-Experts model. It suits general chat, summarization, coding help, function calling, and product flows that expect schema-validated JSON output. It reasons by default; reasoning_effort can be set to none (off) or high (deeper) to adjust the depth. It offers a 128K context window and produces at most 32,768 tokens per response. It accepts text input only.

Technical specifications

Canonical IDopenai/gpt-oss-120b-unmetered
ProviderOpenAI
Context window131,072 tokens
OperationsCHAT_COMPLETIONS
Modalitiestext

Pricing

An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
CHAT_COMPLETIONSINPUT_TEXTPER_1M_TOKENS$0.050000
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$0.250000

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions \
  -H "Authorization: Bearer llmtr-your_key" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-oss-120b-unmetered","messages":[{"role":"user","content":"Hello"}]}'

Related models