gpt-oss-20b-free

by Openai

Developed by OpenAI, gpt-oss-20b-free is an open-weight 21B parameter model released under the Apache 2.0 license. This model utilizes a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass. It supports an expansive context window of up to 131,072 tokens, making it well-suited for long-context tasks.

Specifications

Context window131,072 tokens
Modalitiestext
Featuresreasoning, tool calling, long context
Endpointschat_completions

FAQ

What is gpt-oss-20b-free?

Developed by OpenAI, gpt-oss-20b-free is an open-weight 21B parameter model released under the Apache 2.0 license. This model utilizes a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass. It supports an expansive context window of up to 131,072 tokens, making it well-suited for long-context tasks.

What is the context length of gpt-oss-20b-free?

gpt-oss-20b-free has a 131,072 token context window.

What modalities does gpt-oss-20b-free support?

gpt-oss-20b-free accepts text input.

What features does gpt-oss-20b-free support?

gpt-oss-20b-free supports reasoning, tool calling and long context. Per-protocol parameter support is listed in the capability table on this page.

How do I call gpt-oss-20b-free via API?

gpt-oss-20b-free is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to gpt-oss-20b-free — no other code changes needed.

Who develops gpt-oss-20b-free?

gpt-oss-20b-free is developed by Openai. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

Paid version: gpt-oss-20b

Use gpt-oss-20b-free via the AIHubMix unified API — one interface for every major LLM.