Skip to content
OpenSmartRoute
Model catalogue
Google

Google

Gemma 4 31B (free)

google/gemma-4-31b-it:free

Specification

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

Google

Gemma 4 31B (free)

reasoning open weights toolsfree

Google google/gemma-4-31b-it:free

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
free
Output $/1M
free
Context
262K
Max output
33K
Released
Apr 2, 2026
Modalities
imagetextvideo
Intelligence index-
Coding index43
Agentic index7

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 (free)
targets:
  - id: gemma-4-31b-it-free
    kind: llm
    name: Gemma 4 31B (free)
    metadata:
      model: google/gemma-4-31b-it:free          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 262144
    cost:
      usd_per_1k_tokens: 0.000000