OpenAI GPT-5.1-Codex-Mini vs Z.ai GLM 4.7
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-5.1-Codex-Mini is 1.3× cheaper at a typical mix of 3 input tokens per output token.
- GPT-5.1-Codex-Mini accepts longer prompts: 400K vs 205K tokens.
- GLM 4.7 is the newer model (released 2025-12-22).
| GPT-5.1-Codex-Mini | GLM 4.7 | |
|---|---|---|
| Vendor | OpenAI | Z.ai |
| Released | 2025-11-13 | 2025-12-22 |
| Input / 1M | $0.25 | $0.54 |
| Output / 1M | $2.00 | $1.98 |
| Cached input / 1M | $0.03 | $0.099 |
| Blended / 1M (3:1) | $0.688 | $0.90 |
| Context | 400K | 205K |
| Max output | 128K | 131K |
| Accepts | text, image | text |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 1 | 6 |
| Cheapest provider, output | $2.00 | $1.75 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | — |
Cost calculator
GPT-5.1-Codex-Mini
$45.00 per month$1.50 per day
GLM 4.7
$62.10 per month$2.07 per day
GPT-5.1-Codex-Mini saves $17.10 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare GPT-5.1-Codex-Mini with