Eliminating the 4 Hidden Taxes: AI Tokens, Manual Work, SaaS Cliffs & AI Scrapers Sponsor this header →

Google: Gemma 4 31B API Pricing & Cost Breakdown

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...

google/gemma-4-31b-it
VisionOpen Weight
Last checked: Nov 21, 2026
Input / 1M Tokens
$0.20
Prompt & context tokens
Output / 1M Tokens
$0.40
Generated completion tokens
Blended (3:1) / 1M
$0.25
Tier: ultra-budget
Context Window
262K
Max output: 16K

Technical Specifications

Canonical IDgoogle/gemma-4-31b-it
ProviderGoogle
Input Modalitiesimage, text, video
Output Modalitiestext
Open-WeightYes
Reasoning OptimizedStandard
Vision SupportYes

Estimated Monthly API Spend

StageMonthly TokensEst. Cost
Prototype / MVP
500 req/day
22.5M in / 6.0M out $6.90/mo
Growing SaaS
10,000 req/day
600.0M in / 150.0M out $180.00/mo
Scale Production
100,000 req/day
7500.0M in / 1800.0M out $2,220/mo
Simulate Custom Volume → Cut Cost via 3-Tier Cascade →

Deploy or Route Google: Gemma 4 31B

Open-Weight Inference

Together AI

High-throughput serverless inference & fine-tuning for Llama, DeepSeek, and Qwen.

Run on Together AI →
Dedicated GPUs

RunPod

On-demand H100/A100 GPU pods and serverless vLLM endpoints for private open-weight hosting.

Rent GPUs on RunPod →
Multi-Provider Gateway

OpenRouter

Unified API gateway for 300+ LLMs with automatic fallbacks and unified billing.

Call via OpenRouter →

Some outbound infrastructure and API gateway links on KostoZero are partner referrals that help keep this observatory free and independent at no extra cost to you.

Cheaper Alternatives to Google: Gemma 4 31B

ModelProviderInput / 1MOutput / 1MBlendedContext
NVIDIA: Nemotron 3.5 Super VL NVIDIA $0.15 $0.47 $0.23 1.05M
Anthropic: Claude Haiku 5.5 Anthropic $0.10 $0.50 $0.20 1M
Anthropic: Claude Haiku Latest Anthropic $0.10 $0.50 $0.20 1M
Meta: Muse Ember Meta $0.10 $0.50 $0.20 1.05M
Mistral: Ministral 3 14B 2512 Mistral AI $0.20 $0.20 $0.20 262K
NVIDIA: Nemotron 3.5 Content Safety NVIDIA $0.20 $0.20 $0.20 131K

Frequently Asked Questions

How much does Google: Gemma 4 31B API cost per 1M tokens?

Google: Gemma 4 31B costs $0.20 per 1M input tokens and $0.40 per 1M output tokens ($0.25 blended at a 3:1 ratio).

What is the maximum context window of Google: Gemma 4 31B?

Google: Gemma 4 31B supports up to 262,144 tokens (262K) of input context and up to 16,384 output completion tokens.

What are cheaper alternatives to Google: Gemma 4 31B?

Lower-cost options tracked right now include NVIDIA: Nemotron 3.5 Super VL ($0.23/1M), Anthropic: Claude Haiku 5.5 ($0.20/1M), Anthropic: Claude Haiku Latest ($0.20/1M).

Get Instant Price-Drop (>10%), New AI Bot & SaaS Cliff Alerts

Every 6 hours our autonomous sync checks 40+ LLMs, AI crawlers, and SaaS pricing cliffs—alerting you when prices drop >10% or new scrapers appear.