OpenAI gpt-oss-20b vs Z.ai GLM 5.3 Flash
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- gpt-oss-20b is 1.5× cheaper at a typical mix of 3 input tokens per output token.
- GLM 5.3 Flash accepts longer prompts: 1M vs 131K tokens.
- GLM 5.3 Flash is the newer model (released 2026-08-26).
| gpt-oss-20b | GLM 5.3 Flash | |
|---|---|---|
| Vendor | OpenAI | Z.ai |
| Released | 2025-08-05 | 2026-08-26 |
| Input / 1M | $0.018 | $0.046 |
| Output / 1M | $0.09 | $0.074 |
| Cached input / 1M | $0.0090 | $0.03 |
| Blended / 1M (3:1) | $0.036 | $0.053 |
| Context | 131K | 1M |
| Max output | 33K | 131K |
| Accepts | text | text, image, video |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 10 | 40 |
| Cheapest provider, output | $0.09 | $0.063 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | 1448 ±79 |
| Vendor API status | Operational | — |
Cost calculator
gpt-oss-20b
$2.43 per month$0.08 per day
GLM 5.3 Flash
$3.85 per month$0.13 per day
gpt-oss-20b saves $1.43 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare gpt-oss-20b with