Gemma 4 31B

Google released 2026-04-02 gemma

$0.160 per million tokens, balanced

DeepSeek V4 Flash 0731 scores higher and costs less — but you would give something up.

+22.1 on the capability index and 34% cheaper ($0.105/M against $0.160/M). What you lose:

  • no image, video input

Capability scores do not measure context length, output ceiling or which inputs a model accepts, so a higher score does not mean a drop-in replacement.

The same model via free is 100% cheaper (free/M) — same weights, different latency.

Every price dimension

Input$0.100/M
Output$0.340/M
Cached input$0.100/M

Independent scores

Intelligence29.7
Coding43.4
Agentic14.4
LMArena Elo1441.7default

Sources are listed separately rather than averaged. Across the 62 models both have scored they correlate at r = 0.806 — close agreement overall, but four models rank very differently between them, and a blended score would hide exactly those.

Capability

Context window262K
Max output262K
Input modesimage, text, video
Tool useyes
Reasoningoptional
Open weightsyes

Provenance

Price sourceopenrouter.ai
Fetched2026-08-24
Quality dataverified
Cross-checkedvendor page

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

Markdown for LLMs