Google

Gemma 4 31B

Google's current-generation open-weight model, available across inference gateways for self-hosted and low-cost deployment.

ActiveReleased April 2, 2026Knowledge cutoff January 1, 2025Available from 22 providers
Tool callingCan invoke external tools and APIs (function calling) mid-response.Structured outputCan return JSON or schema-constrained responses instead of free text.ReasoningUses extended thinking / chain-of-thought for harder multi-step problems.Effort controlLets you dial thinking depth (low / medium / high) to trade cost for quality.Fine-tuningSupports training a custom variant on your own data (vendor fine-tune API or self-hosted open weights).

Source: Gemini API models, Gemini API pricing, Gemini deprecations (shutdown dates), Context caching (minimums, implicit vs explicit), Metadata verification, Metadata verification, Field resolution verification

Price per 1M tokens
$0.28 in / $0.86 out
Context window262,144
Max output8,192
ModalitiesText, Image → Text
Priced across22 providers

Pricing

Every billing leg from the live catalog, in USD per 1M tokens.

Billing legRate
Input$0.28 / M
Output$0.86 / M

Cost calculator

Billing-grade math over the rate card above, including the thinking tokens most estimates miss.

Estimated monthly cost
$73.20
at current list prices
Fresh input$56.00
Output$17.20
Track this automatically →

Compare providers

The same model, priced across every platform that serves it. Lowest combined in/out rate is flagged.

PlatformInput / MOutput / MCache read / MBatchAccess
Together AI
$0.28$0.86——Direct
OpeninferenceLowest
$0.08$0.35$0.01—via OpenRouter
DeepInfra
$0.09$0.34$0.05—via OpenRouter
Coreweave
$0.1$0.34$0.1—via OpenRouter
Wandb
$0.12$0.35$0.09—via OpenRouter
Venice
$0.12$0.36$0.09—via OpenRouter
Chutes
$0.12$0.37$0.06—via OpenRouter
SiliconFlow
$0.13$0.4——via OpenRouter
AWS Bedrock
$0.14$0.4—✓Direct
Crusoe
$0.14$0.4$0.14—via OpenRouter
Friendli
$0.14$0.4——via OpenRouter
Morph
$0.14$0.4$0.08—via OpenRouter
Novita
$0.14$0.4——via OpenRouter
AWS Bedrock · Regional
from$0.14$0.4—✓Direct
Parasail
$0.15$0.4$0.06—via OpenRouter
Phala
$0.15$0.46$0.075—via OpenRouter
Modelrun
$0.22$0.55$0.12—via OpenRouter
Together AI
$0.28$0.86——Direct
Together AI
$0.39$0.97——via OpenRouter
Together AI
$0.39$0.97——Direct
SambaNova
$0.38$1.15——via OpenRouter
Cerebras
$0.99$1.49$0.99—via OpenRouter

Regional deployments are priced per region; the lowest available region rate is shown.

Price history

Has this model gotten cheaper or more expensive?

No changePriced at $0.28 / $0.86 per 1M since July 8, 2026.

More from Google

Other models from the same provider.

Gemini 3.7 Flash
google/gemini-3.7-flash
$0.75 / $3.75 in / out per 1M
Gemini 3.6 Flash
google/gemini-3.6-flash
$0.75 / $3.75 in / out per 1M
Gemini 3.5 Flash
google/gemini-3.5-flash
$1.5 / $9 in / out per 1M
Gemini 3.5 Flash-Lite
google/gemini-3.5-flash-lite
$0.3 / $2.5 in / out per 1M
Gemini 3.1 Pro
google/gemini-3.1-pro
$2 / $12 in / out per 1M
Gemini 3 Pro
google/gemini-3-pro
$2 / $12 in / out per 1M

Stop estimating. Track it.

SuperPenguin meters every Gemma 4 31B call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.

Get started free

Rates are generated from SuperPenguin's live pricing catalog.