Available now
OpenAI
gpt-oss-20b
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...
TextReasoningToolsOpen Weights131.1K
InputFree
OutputFree
Context131.1K
Endpointsopenai
Capabilities
ReasoningToolsStructured
Modalities
Input
text
Output
text
Quick stats
Context window131.1K
Max output131.1K
Modechat
TokenizerGPT
Knowledge cutoff2024
Quantizationfp4
Hugging Faceopenai/gpt-oss-20b
Performance
Loading performance data...
Supported parameters
| Parameter | Always | Default |
|---|---|---|
| frequency_penalty | - | (do not send) |
| include_reasoning | - | |
| logit_bias | - | - |
| logprobs | - | - |
| max_tokens | - | |
| min_p | - | - |
| presence_penalty | - | - |
| reasoning | - | |
| repetition_penalty | - | - |
| response_format | - | - |
| seed | - | - |
| stop | - | - |
| structured_outputs | - | - |
| temperature | (do not send) | |
| tool_choice | - | - |
| tools | - | - |
| top_k | - | - |
| top_logprobs | - | - |
| top_p | (do not send) |
§ 01
Pricing
| Input price | $0.00 · 1M tokens |
| Output price | $0.00 · 1M tokens |
| Context window | 131.1K tokens |
| Compatible endpoints | openai |
| Vendor | OpenAI |
§ 02
Call gpt-oss-20b from your code
Point any OpenAI-compatible SDK at UnoRouter and request the model by name. Replace YOUR_API_KEY with a real key from your dashboard.
bash
curl https://api.unorouter.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-oss-20b",
"messages": [{"role": "user", "content": "Hello!"}]
}'§ 03
Frequently asked questions
How much does gpt-oss-20b cost per 1M tokens?
Input is priced at $0.00 per 1M tokens, output at $0.00 per 1M tokens. Billing is per token, no rounding to batch sizes.
How do I access gpt-oss-20b via API?
Send requests to the UnoRouter /v1/chat/completions endpoint with model=gpt-oss-20b. Any OpenAI-compatible client library works. Authentication uses a standard Bearer token.
What is the context window of gpt-oss-20b?
gpt-oss-20b supports a context window of 131.1K tokens, shared between your prompt and the model's response.
§ 04