Google · live price
Gemma 4 31B API pricing
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...
Small and cheap (under $1 per 1M)Tool callingReasoningimage inputvideo input
- Input
- $0.2
- per 1M tokens
- Output
- $0.4
- per 1M tokens
- Cached input
- –
- per 1M tokens
- Context
- 262K
- 16K max output
List price from OpenRouter, which passes Google's price through without markup. Refreshed hourly. Released April 2, 2026. Model id google/gemma-4-31b-it.
What Gemma 4 31B costs in practice
At list price, before any batch or caching discount.
1,000 chat messages
$0.40
1,000 input + 500 output tokens each
1,000 RAG questions
$1.80
8,000 input + 500 output tokens each
100 coding-agent steps
$0.68
30,000 input + 2,000 output tokens each, no caching
Gemma 4 31B price history
Price last changed on 2026-10-27. We record prices daily since 2026-10-01.
Gemma 4 31B price by host
PrimeIntellect serves it below list price right now. Route to it to pay less on every token.
- PrimeIntellect$0.118 in · $0.198 out · 262K ctx · 99.8% uptime 24h
- KT$0.1 in · $0.34 out · 262K ctx · 100.0% uptime 24h
- CoreWeave$0.1 in · $0.34 out · 262K ctx · 92.4% uptime 24h
- Modal$0.34 in · $0.1 out · 131K ctx · 99.3% uptime 24h
- NextBit$0.125 in · $0.34 out · 262K ctx · 100.0% uptime 24h
- Venice$0.12 in · $0.36 out · 256K ctx · 99.9% uptime 24h
- DeepInfra$0.16 in · $0.32 out · 262K ctx · 100.0% uptime 24h
- Chutes$0.12 in · $0.37 out · 131K ctx · 99.3% uptime 24h
- Crusoe$0.14 in · $0.4 out · 260K ctx · 99.9% uptime 24h
- Friendli$0.14 in · $0.4 out · 262K ctx · 100.0% uptime 24h
- Novita$0.14 in · $0.4 out · 262K ctx · 99.5% uptime 24h
- Parasail$0.15 in · $0.4 out · 262K ctx · 100.0% uptime 24h
- SambaNova$0.38 in · $1.15 out · 131K ctx · 96.0% uptime 24h
- ModelRun$0.75 in · $1 out · 262K ctx · 100.0% uptime 24h
- SiliconFlow$0.75 in · $1 out · 262K ctx · 100.0% uptime 24h
Where to buy Google credits for less
Gemma 4 31B costs the same per token everywhere it's sold through OpenRouter. What changes is the price of the credits. Live quotes for $100 of usage:
Gemma 4 31B cost calculator
Enter your monthly tokens to price your own usage.
Usage at list price$14.00/ month
Cheaper alternatives to Gemma 4 31B
Other labs' models in the same price range or the one below, cheaper per token.
| Model | Input / 1M | Output / 1M |
|---|---|---|
| MiniMax: MiniMax M3.1 Flash | $0.075 | $0.3 |
| Anthropic: Claude Haiku 5.5 | $0.1 | $0.5 |
| OpenAI: GPT-6 Luna Pro | $0.1 | $0.5 |
| OpenAI: GPT-6 Luna | $0.1 | $0.5 |
| Qwen: Qwen3.8 Omni Flash | $0.15 | $0.47 |
| DeepSeek: DeepSeek V4.1 Flash | $0.05 | $0.199 |
Other Google models
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Gemma 4 26B A4B | $0.068 | $0.225 |
| Gemini 3.1 Flash Lite Preview | $0.25 | $1.50 |
| Gemini 3.1 Flash Lite | $0.25 | $1.50 |
| Nano Banana 2 (Gemini 3.1 Flash Image Preview) | $0.5 | $3 |
| Gemini 3.1 Pro Preview Custom Tools | $2 | $12 |
| Gemini 3.1 Pro Preview | $2 | $12 |