Gemma 4 31B It

Compare

Gemma 4 31B It

Q: What is the context length of Gemma 4 31B It?

Gemma 4 31B It has a 262,100 token context window. It supports up to 131,100 output tokens.

Q: How much does Gemma 4 31B It cost?

On AIHubMix, Gemma 4 31B It costs $0.14 per million input tokens and $0.4 per million output tokens.

Q: How do I call Gemma 4 31B It via API?

Gemma 4 31B It is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to gemma-4-31b-it — no other code changes needed.

Q: Who created Gemma 4 31B It?

Gemma 4 31B It is developed by Google. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

gemma-4-31b-itllms.txt

Google

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 calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.

Pricing

Input Tokens: $0.140 /M tokens
Output Tokens: $0.400 /M tokens
Cache Read: $0.000 /M tokens

Input Modalities

Output Modalities

Text

Providers

Google AI Studio google-gemma-4-31b-it

Pricing$0.140$0.400

Context262K

Max output131K

Latency1.0S

Throughput34.4TPS

Uptime

98.38% uptime 2 days ago

95.50% uptime yesterday

85.93% uptime today

Cerebras cbs-gemma-4-31b

Pricing$1.000$1.500

Context262K

Max output131K

Latency1.0S

Throughput29.2TPS

Uptime

100.00% uptime 2 days ago

0.00% uptime yesterday

100.00% uptime today

Deepinfra deepinfra-gemma-4-31b-it

Pricing$0.143$0.418

Context128K

Max output128K

Latency1.0S

Throughput39.2TPS

Uptime

100.00% uptime 2 days ago

100.00% uptime yesterday

100.00% uptime today

Performance for gemma-4-31b-it

Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).

Uptime

Latency

Throughput

Try this model

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://aihubmix.com/v1",
)

response = client.chat.completions.create(
    model="gemma-4-31b-it",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

print(response.choices[0].message.content)

Frequently asked questions

What is Gemma 4 31B It?

What is the context length of Gemma 4 31B It?

How much does Gemma 4 31B It cost?

How do I call Gemma 4 31B It via API?

Who created Gemma 4 31B It?

Compare Gemma 4 31B It

Gemma 4 31B ItvsQwen3.8 Max Preview Gemma 4 31B ItvsKimi K3 Gemma 4 31B ItvsGLM 5.2 Gemma 4 31B ItvsGrok 4.5

Gemma 4 31B It

Pricing

Input Modalities

Output Modalities

Providers

Performance for gemma-4-31b-it

Try this model

Frequently asked questions

What is Gemma 4 31B It?

What is the context length of Gemma 4 31B It?

How much does Gemma 4 31B It cost?

How do I call Gemma 4 31B It via API?

Who created Gemma 4 31B It?

Compare Gemma 4 31B It

Product

Company

Developer

Connect

Gemma 4 31B It

Pricing

Input Modalities

Output Modalities

Providers

Performance for gemma-4-31b-it

Try this model

Frequently asked questions

What is Gemma 4 31B It?

What is the context length of Gemma 4 31B It?

How much does Gemma 4 31B It cost?

How do I call Gemma 4 31B It via API?

Who created Gemma 4 31B It?

Compare Gemma 4 31B It

More models from Google

Product

Company

Developer

Connect