← all models
Gemma 4 31B
google
openrouter
ollama cloud
free tier
Parameters
31B
openrouter api · from the model id
Context
256K
262144 tokens
Input
$0.20
OpenRouter · cheapest output
Output
$0.40
OpenRouter · cheapest output
Cache read
$0.10
OpenRouter · cheapest output
Providers
Accepts
image
text
video
Capabilities
frequency_penalty
include_reasoning
logit_bias
logprobs
max_completion_tokens
max_tokens
min_p
presence_penalty
reasoning
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_logprobs
top_p
Description
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...
Also known as
openrouter
google/gemma-4-31b-it
ollama
gemma4:31b
huggingface
google/gemma-4-31B-it
version slug
google/gemma-4-31b-it-20260402
name
Google: Gemma 4 31B
display name
Gemma 4 31B
Identifiers
- Vendor
-
google
- OpenRouter
-
google/gemma-4-31b-it
- Ollama
-
gemma4:31b
- Hugging Face
-
google/gemma-4-31B-it
- Version slug
-
google/gemma-4-31b-it-20260402
- Released
-
2026-04-02T16:48:06.000Z
- First seen
-
59 d ago
- Last crawled
-
16 min ago