Loading
90 days of the enterprise, pro and team plans free, no card needed. See the plans
google/gemma-4-31b-itCatalogue: Indexed in the reference catalogue; nothing on this deployment answers as this model yet.
Published by the vendor; the platform bills at the target's declared price.
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...
Gemma 4 31B earns a request when it needs step-by-step reasoning, tool calls, very long inputs; a short, general request would go to Nemotron 3.5 Super VL (free) instead - free per million input tokens against $0.20 here; and the hardest requests, where the quality floor rules it out, to Claude Opus 5.5 (batch). Your rules decide the floor; the trace shows the comparison for every request.
Lower input price and an intelligence index within 5 points.
Nothing on this deployment answers as this model yet. Connect your own provider under Model providers, or add a target to your catalogue - the router picks it up without retraining.
# 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: 0.000300Input list price per million tokens; Gemma 4 31B is the 2nd cheapest of 13 listed.
Photo: RDNE Stock project
A higher intelligence index, best first, with the price it comes at.
Other models by the same vendor in the catalogue.
The catalogue prints input and output prices and what three typical monthly workloads cost on each.
