AI TOOLS RADAR
All models / GOOGLE
google logo
google

Google: Gemma 4 31B

Source description (English)

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...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
262,144 tokens
Maximum output
235,929 tokens
Architecture
text+image+video->text
Tokenizer
Gemma
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.1
per 1M tokens
Output
$0.34
per 1M tokens
Cache read
$0.1
per 1M tokens
API

Model configuration

Default parameters

temperature
1
top_p
0.95
top_k
64

Reasoning

Reasoning required
No
Default parameters
No
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"google/gemma-4-31b-it","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
imagetextvideo
Output
text
Reasoning

No

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

15 providers

Checked: October 26, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

CoreWeave

fp4
Context
262K
Maximum output
236K
Input
$0.1
Output
$0.34
Cache read
$0.1
Cache write
Not provided

Venice

fp4
Context
256K
Maximum output
8K
Input
$0.12
Output
$0.36
Cache read
$0.09
Cache write
Not provided

Chutes

fp4
Context
131K
Maximum output
66K
Input
$0.12
Output
$0.37
Cache read
$0.012
Cache write
Not provided

DeepInfra

fp4
Context
262K
Maximum output
16K
Input
$0.135
Output
$0.51
Cache read
$0.075
Cache write
Not provided

Crusoe

bf16
Context
262K
Maximum output
262K
Input
$0.14
Output
$0.4
Cache read
$0.14
Cache write
Not provided

Friendli

Not provided
Context
262K
Maximum output
8K
Input
$0.14
Output
$0.4
Cache read
Not provided
Cache write
Not provided

Novita

bf16
Context
262K
Maximum output
131K
Input
$0.14
Output
$0.4
Cache read
Not provided
Cache write
Not provided

Parasail

fp8
Context
262K
Maximum output
236K
Input
$0.15
Output
$0.4
Cache read
$0.06
Cache write
Not provided

DeepInfra

fp8
Context
262K
Maximum output
236K
Input
$0.16
Output
$0.32
Cache read
Not provided
Cache write
Not provided

DeepInfra

fp8
Context
262K
Maximum output
16K
Input
$0.2
Output
$0.4
Cache read
Not provided
Cache write
Not provided

DeepInfra

fp8
Context
262K
Maximum output
236K
Input
$0.3
Output
$0.6
Cache read
Not provided
Cache write
Not provided

Io Net

Not provided
Context
262K
Maximum output
16K
Input
$0.361
Output
$1.0925
Cache read
$0.1805
Cache write
Not provided

SambaNova

Not provided
Context
131K
Maximum output
118K
Input
$0.38
Output
$1.15
Cache read
Not provided
Cache write
Not provided

ModelRun

fp4
Context
262K
Maximum output
236K
Input
$0.75
Output
$1
Cache read
$0.2
Cache write
Not provided

SiliconFlow

fp8
Context
262K
Maximum output
236K
Input
$0.75
Output
$1
Cache read
$0.25
Cache write
Not provided
google

4 models

All models
google logogoogle

Google: Gemini 4 Argon

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...

Context
1.0M
Input
audio · file · image · text · video
Output
text
Input: $2Output: $10per 1M tokens
View model details →
google logogoogle

Google: Gemini 4 Argon (batch)

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...

Context
1.0M
Input
audio · file · image · text · video
Output
text
Input: $1Output: $5per 1M tokens
View model details →
google logogoogle

Google: Nano Banana 2.1

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...

Context
66K
Input
image · text
Output
image · text
Input: $1.5 per 1M tokensOutput: $7.5 per 1M tokens
View model details →
google logogoogle

Google: Gemini 3.5 Transcribe

Gemini 3.5 Transcribe is a speech-to-text model from Google. It is suited for synchronous transcription that needs word-level timestamps or speaker diarization, with support for up to eight speakers. Audio...

Context
98K
Input
audio
Output
transcription
Input: $2 per 1M tokensOutput: $12 per 1M tokens
View model details →