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

$0.14 / $0.42per 1M

Cached price

$0.104per 1M

Context

256K

Max output

16K

Providers

6 routes

Compare providers by price, privacy, and speed.

Tinfoil
TEE$0.48$1.20—262K33K——
VeniceVenice
Private$0.14$0.42$0.104256K16K——
DeepInfraDeepInfra
Private$0.23$0.46—262K16K——
Sail
Private$0.46$0.69$0.23255K131K——
Cheaper Inference
Anonymous$0.33$0.98$0.33262K131K——
Surplus Intelligence
Anonymous$0.17$0.50$0.042262K131K——

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.