Model Release Radar
Price/capability frontier position, benchmark scores, and community signal
Model Release Radar
Qwen3.8 27B
alibaba·open weights·Apache 2.0·released Friday, Aug 14, 2026
USD per million tokens via OpenRouter, Alibaba (alibaba). Checked 2026-10-17 00:21 UTC.
| Token type | USD /1M |
|---|---|
| Input | $0.425 |
| Output | $2.55 |
| Cache read | $0.085 |
| Cache write (default) | Unverified basis |
| Cache write (1 hour) | Unknown |
Cache-write rates with a verified basis replace the ordinary input charge. Unknown rates are never treated as zero.
- Behind frontier AA coding index (blended per-1M-token price, 3:1 input/output; not a measured per-task cost) - Qwen3.5 397B A17B, Gemini 3.5 Flash-Lite, Qwen3.6 Plus, Qwen3.7 Plus, MiMo-V2.5-Pro are priced the same or lower and at least as capable.
- Behind frontier AA intelligence index (blended per-1M-token price, 3:1 input/output; not a measured per-task cost) - Gemini 3.5 Flash-Lite, Qwen3.6 Plus, Qwen3.7 Plus, MiMo-V2.6-Pro, MiMo-V2.5-Pro are priced the same or lower and at least as capable.
This model has not been measured on DeepSWE (or any other benchmark with a real measured per-task cost) yet, so no cost/capability chart is drawn. Its Artificial Analysis benchmark scores are listed below.
Measured cost per task (DeepSWE)
This model has not been measured on DeepSWE (or any other benchmark with a real measured per-task cost) yet.
Artificial Analysis scores
Artificial Analysis scores describe capability. Compare them against estimated token spend with your cache mix; these estimates are not measured task costs.
| Benchmark | Score |
|---|---|
| AA intelligence index | 33.7 |
| AA coding index | 68.1 |
This page covers 4 reasoning-effort variants of the same model.
| Variant | AA coding index | AA intelligence index | Blended /1M (3:1 input/output) |
|---|---|---|---|
| Standard (shown above) | 68.1 | 33.7 | $0.96/1M |
| Low effort | 58.2 | 26.2 | $0.96/1M |
| Medium effort | 56.1 | 27.6 | $0.96/1M |
| Non-reasoning | 44.6 | 20.2 | $0.96/1M |
| Variant | Coding Elo | Overall Elo | Votes |
|---|---|---|---|
| Standard | 1,483 | 1,441 | 23,294 |