Model Release Radar
Price/capability frontier position, benchmark scores, and community signal
Model Release Radar
Gemma 4 31B
google·open weights·Apache 2.0·released Thursday, Apr 2, 2026
USD per million tokens via OpenRouter, CoreWeave (coreweave/fp4). Checked 2026-10-16 22:03 UTC.
| Token type | USD /1M |
|---|---|
| Input | $0.1 |
| Output | $0.34 |
| Cache read | $0.1 |
| Cache write (default) | Unknown |
| 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) - Ling-3.0-flash-VL, DeepSeek V4 Flash 0731, Ling 3.0 Flash 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) - Solar Pro 4, Ling 3.1 Flash, Ling-3.0-flash-VL, Solar Mini 4, Gemma 4 26B A4B 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 | 14.7 |
| AA coding index | 43.4 |
| Variant | Coding Elo | Overall Elo | Votes |
|---|---|---|---|
| Rating | 1,459 | 1,443 | 6,147 |