qwen-max| Provider | Input, $ per 1M | Output, $ per 1M | In our data since |
|---|---|---|---|
| alibaba-cn | $0.345 | $1.377 | 31 Jul 2026 |
| NanoGPT | $1.6 | $6.392 | 31 Jul 2026 |
| Alibaba (Qwen) | $1.6 | $6.4 | 31 Jul 2026 |
| LLM Gateway | $1.6 | $6.4 | 31 Jul 2026 |
Only the base tier and only per-token prices are shown. Batch, discounted and cached rates, as well as prices per image or per second of video, do not go into this table: they cannot stand in the same column as a price per million tokens.
The date in the last column is the day this price first entered our collection. The price may well be older: before that day we simply were not recording it. It has not changed since — otherwise a new row with a new date would stand in its place.
| Task set | Result | Run conditions | Measured by |
|---|---|---|---|
| Arena Score in French | 1,328.73 1,288–1,370 | — | — |
| Arena Score in English | 1,292.71 1,285–1,300 | — | — |
| Arena Score in Spanish | 1,289.07 1,251–1,328 | — | — |
| Arena Score, long queries | 1,288.67 1,277–1,300 | — | — |
| Arena Score, programming | 1,288.56 1,277–1,300 | — | — |
| Arena Score, overall | 1,282.04 1,276–1,288 | — | — |
| Arena Score, multi-turn dialogue | 1,276.75 1,266–1,288 | — | — |
| Arena Score, mathematics | 1,275.05 1,263–1,287 | — | — |
| Arena Score in Russian | 1,273.13 1,261–1,285 | — | — |
| Arena Score, hard prompts | 1,269.73 1,261–1,279 | — | — |
| Arena Score, instruction following | 1,262.28 1,254–1,270 | — | — |
| Arena Score, creative writing | 1,248.48 1,236–1,260 | — | — |
| Arena Score, expert questions | 1,247.54 1,230–1,266 | — | — |