← All modelsGoogle (Gemma) — served by Reka

Gemma 4 31B

Open-weight 31B dense — thinking, tools, image input, 262K context — self-hosted.

Google (Gemma) — served by Reka$0.09 in · $0.34 out / 1M tokens (≤256K ctx)llmgemmaopen-weightsmultimodal
Capabilities
llmgemmaopen-weightsmultimodal
Pricing
Context bandMax tokensInput / M tokOutput / M tok
≤256K262,144$0.09$0.34
API

Wire it up.

EndpointPOST https://api.tryinfer.com/v1/chat/completions
request
curl https://api.tryinfer.com/v1/chat/completions \
-H "Authorization: Bearer $INFER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemma4-31b",
"messages": [{ "role": "user", "content": "Explain the difference between sliding-window and global attention in two short paragraphs." }]
}'

OpenAI-compatible — point your SDK at Infer with a bearer token. Get an API key →