by OpenAIReleased Aug 5, 2025
openai/gpt-oss-20bgpt-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...
| Billed for | You pay |
|---|---|
| Input tokens | $0.022 / 1M |
| Output tokens | $0.11 / 1M |
| Cached input, read | $0.011 / 1M |
$0.022 per million input tokens and $0.11 per million output tokens, paid from the token's AI credit. A call of 2,000 tokens in and 500 out costs about $0.000097.
Make a router key for one of your tokens on the dashboard, point any OpenAI or Anthropic SDK at https://relayfor.si/api/v1 and send the model id openai/gpt-oss-20b. The token's AI credit pays for each call.
Up to 131,072 tokens of context, and up to 32,768 tokens in one answer.
No. The RFS Router passes each call through and keeps only its token counts and cost, for the token's usage page.
import OpenAI from "openai";const ai = new OpenAI({ baseURL: "https://relayfor.si/api/v1", apiKey: process.env.RELAYFOR_ROUTER_KEY,});const reply = await ai.chat.completions.create({ model: "openai/gpt-oss-20b", messages: [{ role: "user", content: "Welcome the 1,000th holder in one line." }],});| Provider | Answered, 24 h |
|---|---|
| Amazon Bedrock | 100% |
| CoreWeavefp4 | 100% |
| Novitafp4 | 99.9% |
| DeepInfrabf16 | 99.9% |
| Darkbloomfp8 | 99.8% |
| Parasailfp4 | 99.6% |
| DekaLLMbf16 | 99.4% |
| AkashMLfp4 | 99% |
| Groq | 97.7% |
| 97.6% | |
| SiliconFlowfp8 | 93.1% |