OpenAI
gpt-oss-20b
openai/gpt-oss-20b
Input
$0.018
per 1M tokens
Output
$0.09
per 1M tokens
Cached input
$0.0090
per 1M tokens
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...
- Released
- Context window
- 131K tokens
- Max output
- 33K tokens
- Input
- text
- Output
- text
- Reasoning
- Yes
Price history
No price changes since we started tracking on .
Providers on OpenRouter
10 endpoints serve this model. Uptime is OpenRouter's share of successful requests; prices per 1M tokens.
| Provider | Input | Output | Context window | Uptime 30 min | Uptime 24 h |
|---|---|---|---|---|---|
| Darkbloomfp8 | $0.018 | $0.09 | 131K | 100% | 100% |
| AkashMLfp4 | $0.02 | $0.10 | 131K | 100% | 100% |
| CoreWeavefp4 | $0.03 | $0.13 | 131K | 100% | 100% |
| DekaLLMbf16 | $0.029 | $0.14 | 131K | 100% | 99.72% |
| DeepInfrabf16 | $0.03 | $0.14 | 131K | 100% | 99.40% |
| Parasailfp4 | $0.03 | $0.15 | 131K | 100% | 99.93% |
| Amazon Bedrock | $0.07 | $0.15 | 131K | 100% | 100% |
| Amazon Bedrockeu-west-1 | $0.07 | $0.15 | 131K | — | 100% |
| SiliconFlowfp8 | $0.04 | $0.18 | 131K | 63.3% | 73.6% |
| Groq | $0.075 | $0.30 | 131K | 100% | 100% |