anonrouter
Sign up
Gemma

Gemma 4 31B

google
Chat

Gemma 4 31B is the dense instruction-tuned model in Google DeepMind's open-weight Gemma 4 family, with about 30.7B parameters. It takes text and image input and produces text output, with a 256K-token context window, configurable thinking, native function calling and pretraining on over 140 languages.

Modalities

In / out price

$0.20 / $0.40per 1M

Context

262K

Max output

16K

Updated

Oct 22, 2026

Providers

4 routes

Compare providers by price, privacy, and speed.

Tinfoil
TEE$0.40$1.00—262K33K——
VeniceVenice
Private$0.12$0.36$0.09256K8K——
DeepInfraDeepInfra
Private$0.20$0.40—262K16K——
Sail
Private$0.40$0.60$0.20255K131K——

Privacy

3 / 4

Hardware-isolated routing

TEE tier

  1. Anonymous
  2. Private
  3. TEE
  4. E2EE

Inference runs inside a hardware-isolated, attestable environment. TEE protects processing, but does not by itself mean the client encrypted the request end to end. Learn more

Features

5
Streaming
Tool calling
Vision
Reasoning
Confidential compute

Uptime

FAQ

Common questions about Gemma 4 31B.