OpenAI / openai/gpt-oss-20b-unmetered

GPT-OSS 20B - access through LLMTR

GPT-OSS 20B is OpenAI's small open-weight Mixture-of-Experts model. It is billed per token with no daily quota, and suits fast chat, classification, data transformation and light automation that needs schema-validated JSON output. It reasons by default; reasoning_effort accepts none or high. tool_choice works with auto and required, but a named function cannot be forced. 128K context, text input only.

Technical specifications

Canonical IDopenai/gpt-oss-20b-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$0.030000
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$0.140000

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-20b-unmetered","messages":[{"role":"user","content":"Hello"}]}'

Related models