qwen3.5-plusThe provider has deprecated this model. It still responds, but it is not a good choice for new projects.
| Provider | Input, $ per 1M | Output, $ per 1M | In our data since |
|---|---|---|---|
| Merge Gateway | $0.115 | $0.688 | 31 Jul 2026 |
| OrcaRouter | $0.115 | $0.688 | 31 Jul 2026 |
| opencode-go | $0.2 | $1.2 | 31 Jul 2026 |
| OpenCode Zen | $0.2 | $1.2 | 31 Jul 2026 |
| EmpirioLabs AI | $0.36 | $2.21 | 31 Jul 2026 |
| meganova | $0.4 | $2.4 | 31 Jul 2026 |
| Alibaba (Qwen) | $0.4 | $2.4 | 31 Jul 2026 |
| NanoGPT | $0.4 | $2.4 | 31 Jul 2026 |
| Vercel | $0.4 | $2.4 | 31 Jul 2026 |
| alibaba-cn | $0.573 | $3.44 | 31 Jul 2026 |
| ZenMux | $0.8 | $4.8 | 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 |
|---|---|---|---|
| Mock AIME 2024–2025 — olympiad problems | 84.99 % | · with a tuned harness | Epoch evaluations |
| GPQA Diamond — graduate-level questions | 78.87 % | · with a tuned harness | Epoch evaluations |
| SimpleQA Verified — factual accuracy | 26 % | — | Epoch evaluations |
| APEX-Agents | 13.6 % | — | — |
| Chess puzzles | 12.67 % | — | Epoch evaluations |