Gemma 4 31B

google/gemma-4-31b-it

Compare with Gemma 4 26B A4B , Gemma 4 26B A4B (free), Gemma 4 31B (free)

Showing only the deepinfra/fp8 provider · show all 17

CompareGemma 4 31B

	State
DeepInfradeepinfra/fp8fp8	Healthy	99.95%	98.31%	90.51%	90.51%	401ms	2.60s	50 tps	262K	$0.130 / $0.380

DeepInfra99.95%
Healthy24h 98.31%
7d
90.51%
30d
90.51%
p50
401ms
p99
2.60s
Throughput
50 tps
Context
262K
$/Mtok
$0.130 / $0.380
deepinfra/fp8fp8

Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

Price changes

Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 12:50 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 12:45 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 12:40 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 12:35 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 12:30 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 12:25 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 12:20 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 12:15 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 12:10 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 12:05 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 12:00 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 11:55 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 11:50 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 11:45 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 11:40 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 11:35 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 11:30 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 11:25 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 11:20 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 11:15 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 11:10 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 11:05 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 11:00 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 10:55 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 10:50 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 10:45 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 10:40 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 10:35 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 10:30 UTC
Gemma 4 31B Togethertogether$0.390 / $0.970 → $0.280 / $0.8602026-08-21 10:25 UTC

History

Availability

Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.

Time to first token

Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window.

Throughput

Median tokens per second.