kilo-logo
kilo-logo
kilo-logo

/

/

Gemma 4 31B-it FP8

Gemma 4 31B-it FP8

by Google

Gemma 4 31B-it FP8 pricing, context window and specs

Gemma 4 31B-it FP8 is a Google model with a 262,144 token context window. It costs $0.39 per million input tokens and $0.97 per million output tokens, and supports image input, reasoning, tool calling and structured output.

Gemma 4 31B-it FP8google/gemma-4-31B-it
Updated Nov 20, 2026
Input price$0.39per 1M tokens
Output price$0.97per 1M tokens
Context window262,144tokens, about 197,000 words
Tool callingStructured outputVisionReasoning

Gemma 4 31B-it FP8 specs

Provider

Google

Model ID

google/gemma-4-31B-it

Input price

$0.39 per 1M tokens

Output price

$0.97 per 1M tokens

Context window

262,144 tokens

Modalities

Text and images in, text out

Tool calling

โœ“ Supported

Structured output

โœ“ Supported

Reasoning

โœ“ Supported

Vision

โœ“ Supported

Prices checked on

When to use Gemma 4 31B-it FP8

Pick Gemma 4 31B-it FP8 for work you run in bulk, where the cost of each call matters more than depth.

High volume steps. Classifying, tagging, routing and pulling fields out of text.

Problems that need thinking. It can reason through a task before it answers.

Agents that use tools. It supports tool calling and structured output, so it can act and hand back clean JSON.

Large inputs. The 262,144 token context window fits long documents and transcripts in one request.

Reading images. It accepts screenshots, scans and photos alongside text.

If you need more capability, Gemini 2.5 Flash costs $1.00 per million input tokens.

Cost calculator

What Gemma 4 31B-it FP8 costs at your volume

Pick a workload or move the sliders. The estimate uses the prices in the table above.

Start from a workload
Estimated Gemma 4 31B-it FP8 cost per month$13.14
Input 67%Output 33%
Per request$0.00088
Per day$0.44
Per 1,000 requests$0.88
Context window used0.7% of 262.1K

Worked out from the provider list price. Fetch Hive charges that price to your AI wallet with no markup per call, and each model call uses one task from your plan.

Templates

Templates you can run with Gemma 4 31B-it FP8

Ready-made workflows and agents. Copy one, pick Gemma 4 31B-it FP8 in the AI step and run it.

Build with it

Use Gemma 4 31B-it FP8 in Fetch Hive

Fetch Hive is an AI agent builder. Pick this model in any prompt, workflow or agent step, or call it from your own code with one API request.

Call Gemma 4 31B-it FP8 through the AI Gateway

1

Create a prompt and pick the model

Write your prompt in Fetch Hive and choose this model from the model library. Add a fallback model if you want a backup.

2

Deploy the prompt

Deploying gives the prompt a deployment name and a variant that your code can call.

3

Send one POST request

Call the invoke endpoint with your API key. Usage is charged to your AI wallet at the provider list price, and each call uses one task.

bash
curl -X POST \
  https://api.fetchhive.com/v1/prompt/invoke \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "deployment": "your-deployment",
    "variant": "default",
    "inputs": { "ticket": "Where is my order?" },
    "streaming": false
  }'

Compare

Compare Gemma 4 31B-it FP8 with similar models

List prices per 1M tokens and context window, next to the models people most often weigh it against.

VS

Gemini 3.5 Flash Lite

by Google
Gemma 4 31B-it FP8Gemini 3.5 Flash Lite
Input per 1M tokens23% cheaper
$0.39
$0.30
Output per 1M tokens2.4x cheaper
$0.97
$0.40
Context window4x larger
262K tokens
1.05M tokens
See Gemini 3.5 Flash Lite pricing and specs
VS

Gemini 2.5 Flash Lite

by Google
Gemma 4 31B-it FP8Gemini 2.5 Flash Lite
Input per 1M tokens23% cheaper
$0.39
$0.30
Output per 1M tokens2.4x cheaper
$0.97
$0.40
Context window4x larger
262K tokens
1.05M tokens
See Gemini 2.5 Flash Lite pricing and specs
VS

GPT 4.1 Mini

by OpenAI
Gemma 4 31B-it FP8GPT 4.1 Mini
Input per 1M tokens3% pricier
$0.39
$0.40
Output per 1M tokens65% pricier
$0.97
$1.60
Context window4x larger
262K tokens
1.05M tokens
See GPT 4.1 Mini pricing and specs

FAQ

Gemma 4 31B-it FP8 questions, answered

Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image

Build with Gemmma 4 31B-it FP8

on Fetch Hive today.

Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image

Build with Gemmma 4 31B-it FP8

on Fetch Hive today.

Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image
Agent Image

Build with Gemmma 4 31B-it FP8

on Fetch Hive today.