Google: Gemma 4 31B
google/gemma-4-31b-it
Cheaper than 87% of paidReasoningToolsJSONVision
Intelligence
—
Design Elo
—
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.100
44th cheapest
Context
262K
262K max out
How it compares
Cheaper than87%
of all ranked models
Overview
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...
Providers & pricing (18)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfrafp4 | $0.090 | $0.340 | 262K | 97.7% |
| CoreWeavebf16 | $0.100 | $0.340 | 262K | 99.8% |
| OpenInferencebf16 | $0.100 | $0.350 | 262K | 97.7% |
| Venicebf16 | $0.120 | $0.360 | 256K | 99.4% |
| Chutesfp4 | $0.120 | $0.370 | 131K | 97.4% |
| DeepInfrafp8 | $0.130 | $0.380 | 262K | 91.2% |
| SiliconFlowfp8 | $0.130 | $0.400 | 262K | 97.1% |
| Novitabf16 | $0.140 | $0.400 | 262K | 97.8% |
| Friendli | $0.140 | $0.400 | 262K | 99.9% |
| Morphfp4 | $0.140 | $0.400 | 175K | 98.3% |
| Crusoe | $0.140 | $0.400 | 262K | 99.1% |
| Parasailfp8 | $0.150 | $0.400 | 262K | 98.2% |
| Phala | $0.150 | $0.460 | 262K | 98.2% |
| ModelRunfp4 | $0.220 | $0.550 | 262K | 99.8% |
| Together | $0.280 | $0.860 | 262K | 92.7% |
| SambaNova | $0.380 | $1.15 | 131K | 99.9% |
| Together | $0.390 | $0.970 | 262K | 85.8% |
| Cerebrasfp16 | $0.990 | $1.49 | 131K | 100% |
Specifications
Context window262K
Max output262K
Knowledge cutoff—
Input modalitiesimage, text, video
Output modalitiestext
Prompt caching—
Cache read price$0.100/M
ModeratedNo
Open weightsgoogle/gemma-4-31B-it ↗
Gemma 4 31B FAQ
How much does Gemma 4 31B cost?
Gemma 4 31B costs $0.100 per million input tokens and $0.340 per million output tokens via OpenRouter, making it 44th cheapest of 332 paid models.
What is Gemma 4 31B's context window?
Gemma 4 31B supports a 262K-token context window and can output up to 262K tokens. It accepts image, text, video input.
More from google
All Gemma 4 31B alternatives →Compare head-to-head
Google: Gemma 4 31B vs Google: Gemini 3.6 FlashGoogle: Gemma 4 31B vs Google: Gemini 3.6 Flash (batch)Google: Gemma 4 31B vs Google: Gemini 3.5 Flash LiteGoogle: Gemma 4 31B vs Google: Gemini 3.5 Flash Lite (batch)Google: Gemma 4 31B vs Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google: Gemma 4 31B vs Google: Nano Banana 2 (Gemini 3.1 Flash Image)