gpt-oss-20b (batch)

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.

ChatOpenAI131k tokens$0.0545 / $0.218 · 1M

openai/gpt-oss-20b:batch

Context
131k tokens
Completion cap
117,964
Tools
No
JSON
Yes
Released
2025-08-05

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-oss-20b:batch",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is gpt-oss-20b (batch)?
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs. gpt-oss-20b (batch) runs on the Geek Hub API (OpenAI-compatible). Model id: openai/gpt-oss-20b:batch.
Is gpt-oss-20b (batch) free?
No. Input is $0.0545 per 1M tokens and output is $0.218 per 1M tokens on Geek Hub (markup included).
What is the context length of gpt-oss-20b (batch)?
gpt-oss-20b (batch) has a 131k tokens context window. It supports up to 117,964 completion tokens.
Does gpt-oss-20b (batch) support tool calling and structured outputs?
gpt-oss-20b (batch) does not advertise tool calling on this endpoint. It also supports structured outputs via a JSON schema in response_format.
When was gpt-oss-20b (batch) released?
gpt-oss-20b (batch) was released on 2025-08-05.

More models from OpenAI