Gemma 4 31B IT

GoogleMCP Tool CallReasoning
google/gemma-4-31b-itOpen Weights

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

Benchmark Pricing$0.22 / 1M in$0.39 / 1M out
Context: 262,144 tokens•Max Output: 32,768 tokens•Knowledge: 2025-01•Released: 2026-04-02

TECHNICAL SPECIFICATIONS

Context Window262,144262.1K tokens
Max Output32,76832.8K tokens
LicenseOpen SourceSelf-hostable
Input Modalities
TextVision
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Gemma 4 31B IT natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 262,144 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling Gemma 4 31B IT via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.GOOGLE_API_KEY,
});

const response = await client.chat.completions.create({
  model: "google/gemma-4-31b-it",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);

PRICING BY PROVIDER

15 providers
Cortecsgemma-4-31b-it
$0.22 / $0.39
AMDGemma-4-31B-IT
$0.00 / $0.00$0.00 cache
NanoGPTgemma-4-31b-it-darkidol
$0.10 / $0.45$0.05 cache
Novita AIgoogle/gemma-4-31b-it
$0.14 / $0.40
ai&google/gemma-4-31b-it
$0.20 / $0.50$0.05 cache
Lilacgoogle/gemma-4-31b-it
$0.11 / $0.35
LLM Gatewaynovita/gemma-4-31b-it
$0.14 / $0.40
QVACgemma4-31b
$0.00 / $0.00
Friendligoogle/gemma-4-31B-it
$0.14 / $0.40
AI/ML APIgoogle/gemma-4-31b-it
$1.36 / $2.05$1.36 cache
Venice AIgoogle-gemma-4-31b-it
$0.12 / $0.36$0.09 cache
Abacusgoogle/gemma-4-31b-it
$0.14 / $0.40
Vercel AI Gatewaygoogle/gemma-4-31b-it
$0.14 / $0.40
UnoRoutergemma-4-31b-it:free
$0.00 / $0.00
Merge Gatewaygoogle/gemma-4-31b-it
$0.14 / $0.40

Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.

MODEL RESOURCES

View Google HubHugging Face Weights

More Models by Google

Alternative and family models from the same lab

View all Google models →
Gemini 3.6 Flash
google/gemini-3.6-flash•Google
1M ctx

Fast Gemini model balancing multimodal reasoning, tool use, and cost

65.5K out maxVisionPDFSWE-Bench Pro: 58.7 resolve rate
In: $0.75 • Out: $3.75
Google
Gemini 2.5 Flash
google/gemini-2.5-flash•Google
1M ctx

Fast Gemini workhorse for multimodal apps where latency and price matter

65.5K out maxVisionPDFAider Polyglot: 55.1 percent correct
In: $0.30 • Out: $2.50
Google
Gemini Omni 1.1 Flash
google/gemini-omni-1.1-flash•Google
1M ctx

Video generation and editing model for scene extension, frame interpolation, and reference-guided multimodal control

57.9K out maxVision
In: $1.52 • Out: $9.09
Google