Google · Model identity
Gemma 4 31B
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...
2pricing routes
What published route metadata supports
Hugging FaceReasoningStructured outputTool useVideo inputVision
Input modalities
ImageTextVideo
Supported API parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Only source-backed fields are filled
Release dateNot independently verified
Knowledge cutoffNot independently verified
Open weightsNot independently verified
OpenRouter catalog date2026-04-02
LLMPrice does not infer a release date, knowledge cutoff, or open-weight status from a model name, Hugging Face link, or pricing route.
Could this workload cost less?Compare Gemma 4 31B with cheaper models using the same workload.
Find cheaper alternatives →| Endpoint / route | Model ID | Input | Cached | Output | Context | Source |
|---|---|---|---|---|---|---|
| OpenRouterFree | google/gemma-4-31b-it:free | $0 | — | $0 | 262K | OpenRouter API ↗ |
| OpenRouterStandard | google/gemma-4-31b-it | $0.2 | — | $0.4 | 262K | OpenRouter API ↗ |
Hugging Face references
Presence of a Hugging Face ID is not treated as proof that model weights are open.
1 verified price change since Aug 26, 2026
2 route availability changes recorded. No earlier prices are inferred.
Input / 1M$0.2Aug 26, 2026 → Oct 15, 2026
Output / 1M$0.4Aug 26, 2026 → Oct 15, 2026
- Oct 15, 2026OpenRouter · Standard
Input $0.09 → $0.2 · Cached input $0.05 → — · Output $0.34 → $0.4
- Sep 16, 2026OpenRouter · Batch
Pricing route removed
- Aug 28, 2026OpenRouter · Batch
New pricing route added