OpenAI: gpt-oss-20b
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...
Modalities
In / Out Price
$0.018 / $0.09 per 1M
Context
131K
Released
Aug 5, 2025
Knowledge Cutoff
Jun 2024
Providers
Different carriers host the same model. Reroute routes each request to the best one on price and uptime, and fails over to the next if a carrier goes down.
| Provider | Context | Input /M | Output /M | Cache read /M | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|---|
 Darkbloomfp8 | 131K | $0.018 | $0.09 | $0.009 | — | — | 100.00% |
 AkashMLfp4 | 131K | $0.02 | $0.10 | — | — | — | 100.00% |
 DekaLLMbf16 | 131K | $0.029 | $0.14 | $0.029 | — | — | 100.00% |
 CoreWeavefp4 | 131K | $0.03 | $0.13 | $0.03 | — | — | 100.00% |
 DeepInfrabf16 | 131K | $0.03 | $0.14 | — | — | — | 100.00% |
 Parasailfp4 | 131K | $0.03 | $0.15 | $0.02 | — | — | 100.00% |
 SiliconFlowfp8 | 131K | $0.04 | $0.18 | — | — | — | 100.00% |
 Amazon Bedrock | 131K | $0.07 | $0.15 | — | — | — | 100.00% |
| Amazon Bedrock | 131K | $0.07 | $0.15 | — | — | — | 100.00% |
 Google | 131K | $0.07 | $0.25 | — | — | — | 100.00% |
 Groq | 131K | $0.075 | $0.30 | $0.0375 | — | — | 100.00% |