OpenAI: gpt-oss-20b (free)
OpenAI: gpt-oss-20b (free) ranks #77 of 85 models by Artificial Analysis quality score (15.2) at $0.05/1M tokens blended - and ranks #50 of 291 by average real OpenRouter usage share over the trailing 35-day window (0.30%).
- Quality (Intelligence Index) - 15.2
- Coding index - 20.7
- Agentic index - 3.1
- Price (blended $/1M) - 0.05
- Context window - 131,072
- Usage rank - #50 of 291
- Providers - 0
- Open/closed - open
Usage share over time
What OpenAI: gpt-oss-20b (free) is actually used for
Share of each real task category's classified traffic this model handles, from OpenRouter's task classification.
| Task | Share of task traffic |
|---|---|
| Tool Dispatch | 4.3% |
| Math | 3.6% |
| Finance & Trading | 3.6% |
| Memory Extraction | 3.5% |
| Web Search | 2.9% |
| Data Transformation | 2.7% |
Frequently asked questions
What is OpenAI: gpt-oss-20b (free)'s quality score?
OpenAI: gpt-oss-20b (free) scores 15.2 on Artificial Analysis's Intelligence Index, ranking #77 of 85 models with a published score.
How much does OpenAI: gpt-oss-20b (free) cost?
OpenAI: gpt-oss-20b (free) costs $0.05 per 1M tokens (blended 75% prompt / 25% completion pricing).
Is OpenAI: gpt-oss-20b (free) widely used?
OpenAI: gpt-oss-20b (free) ranks #50 of 291 models by average real OpenRouter usage share, averaging 0.30% of classified token volume over the trailing 35-day window.
Is OpenAI: gpt-oss-20b (free) open-weight or closed?
OpenAI: gpt-oss-20b (free) is an open-weight model.
Source: OpenRouter (openrouter.ai/rankings), as of August 9, 2026.
Benchmark scores: Artificial Analysis (artificialanalysis.ai) via OpenRouter (openrouter.ai/rankings).
Methodology: smophy.ai/benchmark/methodology
Token counts originate from each provider's own tokenizer and are not directly comparable across providers.