OpenAI GPT-4o-mini (2024-07-18) vs Qwen3 235B A22B Instruct 2507
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
- Qwen3 235B A22B Instruct 2507 is 1.3× cheaper at a typical mix of 3 input tokens per output token.
- Qwen3 235B A22B Instruct 2507 accepts longer prompts: 262K vs 128K tokens.
- Qwen3 235B A22B Instruct 2507 output costs $0.35 per 1M via GMICloud, against the list price of $0.55.
- Qwen3 235B A22B Instruct 2507 is the newer model (released 2025-07-21).
| GPT-4o-mini (2024-07-18) | Qwen3 235B A22B Instruct 2507 | |
|---|---|---|
| Vendor | OpenAI | Qwen |
| Released | 2024-07-18 | 2025-07-21 |
| Input / 1M | $0.15 | $0.09 |
| Output / 1M | $0.60 | $0.55 |
| Cached input / 1M | $0.075 | — |
| Blended / 1M (3:1) | $0.262 | $0.205 |
| Context | 128K | 262K |
| Max output | 16K | 16K |
| Accepts | text, image, file | text |
| Reasoning | No | No |
| Providers on OpenRouter | 1 | 5 |
| Cheapest provider, output | $0.60 | $0.35 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | Operational |
Cost calculator
GPT-4o-mini (2024-07-18)
$18.00 per month$0.60 per day
Qwen3 235B A22B Instruct 2507
$13.65 per month$0.46 per day
Qwen3 235B A22B Instruct 2507 saves $4.35 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare GPT-4o-mini (2024-07-18) with
Compare Qwen3 235B A22B Instruct 2507 with