Google: Gemma 4 31B

GoogleOpen weights

Google: Gemma 4 31B by Google costs $0.20 per 1M input tokens and $0.40 per 1M output tokens, with a 262K-token context window.

Pricing

Input (per 1M tokens)

$0.20

Output (per 1M tokens)

$0.40

Cached input (per 1M)

—

Specifications

Provider: Google
Context window: 262K tokens
Parameters: —
Released: Apr 2026
Open weights: Yes
Frontier model: No
Hugging Face: google/gemma-4-31B-it

Benchmarks

LMArena (Chatbot Arena) Elo: 1442.8
LMArena Vision Elo: 1276.8
LMArena WebDev Elo: 1366.1

Speed & latency

Time to first token

0.53s

Output speed

30 tok/s

Fastest host: novita (via hf-router).

Compare Google: Gemma 4 31B with…

Google: Gemma 4 31B vs GPT-4.1 Nano$0.40/1M Google: Gemma 4 31B vs Qwen3.5 Flash$0.40/1M Google: Gemma 4 31B vs Gemini 2.5 Flash Lite$0.40/1M Google: Gemma 4 31B vs GPT-5 Nano$0.40/1M Google: Gemma 4 31B vs GLM 4.7 Flash$0.40/1M Google: Gemma 4 31B vs Llama 3.1 70B Instruct$0.40/1M

FAQ

How much does Google: Gemma 4 31B cost?

Google: Gemma 4 31B is priced at $0.20 per 1M input tokens and $0.40 per 1M output tokens. Output tokens cost more than input.

What is Google: Gemma 4 31B's context window?

Google: Gemma 4 31B supports a context window of 262K tokens — the maximum prompt plus response length it can handle in a single request.

Is Google: Gemma 4 31B open weight?

Yes — Google: Gemma 4 31B has openly available weights.

Data as of 2026-10-15. Source: Pricing via OpenRouter API, openrouter.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.