Capabilities
7-day heat trend
+4.3%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 41% of tracked models
- Faster than 11% of tracked models
- Efficiency rank: #430 of 1105
Best suited for
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
About 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...
gpt-oss-20b is a Text model from OpenAI (US). HotON.ai tracks it at $0.03 per 1M input tokens and $0.14 per 1M output tokens, with a 131K-token context window, ~126 tokens/sec throughput and 98.6% availability. Its composite efficiency score is 89/100 at an estimated $0.000 per successful task.
Compare gpt-oss-20b
Related market news
Frequently asked questions
How much does gpt-oss-20b cost per 1M tokens?+
gpt-oss-20b is tracked at $0.03 per 1M input tokens and $0.14 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $0.11 per 1M tokens. Figures are illustrative demo data.
What is gpt-oss-20b best for?+
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
How fast is gpt-oss-20b?+
gpt-oss-20b delivers about 126 tokens/sec with 98.6% tracked availability, suitable for latency-sensitive, real-time applications.
Is gpt-oss-20b cheaper than other AI models?+
Within the HotON.ai tracked set, gpt-oss-20b is cheaper than 41% of models on input price and ranks #430 of 1105 by overall efficiency.
Related models
Pricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Speed, availability and efficiency are modeled estimates.