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
Pricing
What Reroute charges per unit. No markup on inference — you pay the carrier's price, metered from the carrier's own usage numbers.
Input tokens
$0.018 / M
Output tokens
$0.09 / M
Cache read
$0.009 / M
By provider
Each carrier sets its own price. The router weighs these against uptime when it picks one.
| Provider | Input /M | Output /M | Cache read /M | Cache write /M | Discount |
|---|---|---|---|---|---|
 Darkbloom | $0.018 | $0.09 | $0.009 | — | — |
 AkashML | $0.02 | $0.10 | — | — | — |
 DekaLLM | $0.029 | $0.14 | $0.029 | — | — |
 CoreWeave | $0.03 | $0.13 | $0.03 | — | — |
 DeepInfra | $0.03 | $0.14 | — | — | — |
 Parasail | $0.03 | $0.15 | $0.02 | — | — |
 SiliconFlow | $0.04 | $0.18 | — | — | — |
 Amazon Bedrock | $0.07 | $0.15 | — | — | — |
| Amazon Bedrock | $0.07 | $0.15 | — | — | — |
 Google | $0.07 | $0.25 | — | — | — |
 Groq | $0.075 | $0.30 | $0.0375 | — | — |