gpt-oss-20b (low)
AI model by OpenAI. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. gpt-oss-20b (low) is a budget-tier option from OpenAI at $0.20/M output tokens. Despite the low price, it scores competitively on measurable benchmarks — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, gpt-oss-20b (low) reports 170 tok/s output speed and 1080ms time-to-first-token. Output speed is in the normal range — most chat and completion applications will be token-bound, not streaming-bound.
Cost model. For a workload of 1M input tokens + 100K output tokens, gpt-oss-20b (low) costs $0.09 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
gpt-oss-20b (low)Current | $0.07 | $0.20 | 170 tok/s |
| NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) | $0.05 | $0.20 | 225 tok/s |
| Qwen3.5 9B (Reasoning) | $0.14 | $0.20 | 81 tok/s |
| NVIDIA Nemotron Nano 9B V2 (Non-reasoning) | $0.05 | $0.20 | 168 tok/s |
| Qwen2.5 Turbo | $0.05 | $0.20 | 108 tok/s |
| Ministral 3 14B | $0.20 | $0.20 | 85 tok/s |