gpt-oss-20b (free)
OpenAI
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...
What is gpt-oss-20b (free)?
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...
Specifications
- Developer: OpenAI
- Context window: 131.1K tokens
- Max output: 8.2K tokens
- Input modalities: text
- Output modalities: text
- Input price: Free per 1M tokens
- Output price: Free per 1M tokens
- Knowledge cutoff: 2024-06-30
- Supported parameters: include_reasoning, max_tokens, reasoning, seed, stop, temperature, tool_choice, tools
Use gpt-oss-20b (free) with PromptLayer
PromptLayer lets teams manage, evaluate, and observe prompts that run on gpt-oss-20b (free) alongside every other model in their stack. Version prompts, run evals across models, and ship safe rollouts from the same dashboard.
Ready to try it yourself? Sign up for PromptLayer and start managing your prompts in minutes.