What is the context window of Google: Gemma 4 31B?

Google: Gemma 4 31B accepts up to 262,144 tokens (262K) of context per request.

How much does Google: Gemma 4 31B cost per million tokens?

Through Wide Area Intelligence, Google: Gemma 4 31B costs $0.099 per 1M input tokens and $0.37 per 1M output tokens when served from the cloud, billed from prepaid credits. A workload of 1M input plus 1M output tokens costs $0.47.

Can I run Google: Gemma 4 31B on my own hardware?

Yes — Google: Gemma 4 31B is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 21.3 GB of GPU memory with an 8,192-token context — it fits a single 24 GB card. Wide Area Intelligence routes requests to your own nodes first and fails over to the cloud only when they can't serve.

← model directory

google

Google: Gemma 4 31B

Name: Google: Gemma 4 31B
Brand: google
Price: 0.0990 USD

google/gemma-4-31b-it

↓ runs free on your own hardware⚙ tool calling

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...

specs & pricing

Type: text
Provider: google
Model ID: google/gemma-4-31b-it
Capabilities: vision, tools, reasoning
Context window: 262K tokens
Self-hostable: Yes — runs on your own GPU
Input price: $0.099 / 1M tokens
Output price: $0.37 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.

What it costs to run

cloud · 1M in + 1M out

$0.47

$0.099 for a million input tokens plus $0.37 for a million output tokens, billed from credits only when a request fails over to the cloud.

your hardware

$0 / token

Served from a workstation or on-prem server you own, there is no per-token fee — the marginal cost is power.

AI cost calculator →GPU power cost →

Run it on your own hardware

Estimated GPU memory for Google: Gemma 4 31B (33B parameters), including the KV cache for a 8,192-token context.

Q4_K_M: ~21.3 GBfits a 24 GB card
Q8_0: ~35.0 GBfits a 48 GB card
FP16 / BF16: ~63.7 GBfits a 80 GB card

Install the agent on the machine and it dials out to the gateway over a single WebSocket — no port forwarding or inbound firewall rules. Requests for this model go to your node first and fail over to the cloud only when it can't serve.

VRAM calculator →Which GPU do I need? →

/// initialize

Call Google: Gemma 4 31B through one OpenAI-compatible endpoint.

Serve it from hardware you own, with cloud failover when your nodes are busy or offline.

Run it on your own hardware Try it in chat

no credit card · 2 nodes free · openai-compatible

Frequently asked questions

What is the context window of Google: Gemma 4 31B?: Google: Gemma 4 31B accepts up to 262,144 tokens (262K) of context per request.
How much does Google: Gemma 4 31B cost per million tokens?: Through Wide Area Intelligence, Google: Gemma 4 31B costs $0.099 per 1M input tokens and $0.37 per 1M output tokens when served from the cloud, billed from prepaid credits. A workload of 1M input plus 1M output tokens costs $0.47.
Can I run Google: Gemma 4 31B on my own hardware?: Yes — Google: Gemma 4 31B is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 21.3 GB of GPU memory with an 8,192-token context — it fits a single 24 GB card. Wide Area Intelligence routes requests to your own nodes first and fails over to the cloud only when they can't serve.

More from google

← browse all models