Google

Gemma 4 31B

google/gemma-4-31b-it

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

Gemma 4 31B

reasoning open weights tools

Google google/gemma-4-31b-it

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...

Input $/1M: $0.09
Output $/1M: $0.34
Context: 262K
Max output: 16K
Released: Apr 2, 2026
Modalities: imagetextvideo

Intelligence index-

Coding index43

Agentic index7

Cached input reads $0.05 per 1M · weights on Hugging Face as google/gemma-4-31B-it

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs Gemma 4 31B
targets:
  - id: gemma-4-31b-it
    kind: llm
    name: Gemma 4 31B
    metadata:
      model: google/gemma-4-31b-it          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 262144
    cost:
      usd_per_1k_tokens: 0.000215

Price among Google models

Input list price per million tokens; Gemma 4 31B is the cheapest of 13 listed.

1
Gemma 4 31B
$0.09
2
Gemini 3.5 Flash Lite (batch)
$0.15
3
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
$0.25
4
Gemini 3.5 Flash Lite
$0.30
5
Gemini 3.8 Flash (batch)
$0.38
6
Gemini 3.7 Flash (batch)
$0.38
7
Gemini 3.6 Flash (batch)
$0.38
8
Nano Banana 2 (Gemini 3.1 Flash Image)
$0.50
9
Gemini 3.8 Flash
$0.75
10
Gemini 3.7 Flash
$0.75
11
Gemini 3.6 Flash
$0.75
12
Gemini 3.5 Flash
$1.50

More from Google

Other models by the same vendor in the catalogue.