Google

Gemma 4 31B Instruct API Pricing 2026

Compare pricing, benchmarks, and providers for Gemma 4 31B Instruct. Find the best value for your use case.

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

Gemma 4 31B Instruct was released on April 2, 2026. Pricing starts at $0.100 per million input tokens and $0.100 per million output tokens. The model supports a context window of up to 262K tokens. API access is available through Google.

Context Window
262K
tokens
Pricing
Input$0.100
Output$0.100
Cached$0.012
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
VisionTools

Gemma 4 31B Instruct is priced at $0.100 per million input tokens and $0.100 per million output tokens. It has a context window of 262,144 tokens. It is available from 18 providers, with CoreWeave the cheapest at $0.100 per million input tokens (input prices range from $0.100 to $0.900). Over the past ~90 days its cheapest input price has risen 25%, from $0.080 to $0.100 per million tokens.

Pricing Comparison

Compare Gemma 4 31B Instruct with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$0.100
$0.100
—
—
—
262,144
Try
$0.090
$0.290
—
—
—
262,144
Try
$0.090
$0.300
—
—
—
256,000
Try
$0.090
$0.900
—
—
—
262,144
Try
$0.090
$0.300
—
—
—
262,144
Try
$0.090
$0.500
—
—
—
32,768
Try
$0.090
$0.180
—
—
—
262,144
Try
$0.093
$0.373
—
—
—
131,072
Try
$0.100
$0.625
—
—
—
400,000
Try
$0.100
$0.100
—
—
—
16,384
Try
$0.100
$0.200
—
—
—
65,536
Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

Gemma 4 31B Instruct is available from multiple providers with different pricing and availability.

18
Providers
$0.100
Cheapest Input/M
$0.100
Cheapest Output/M
CoreWeave
Best Price

Provider Pricing

18 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Input $/M
Output $/M
Cache Read $/M
Cache Write $/M
Uptime
C
CoreWeave
Best Price
$0.100
$0.340
$0.100
-
100.0%
V
Venice
$0.120
$0.360
$0.090
-
100.0%
C
Chutes
$0.120
$0.370
$0.012
-
100.0%
N
NextBit
$0.125
$0.340
$0.075
-
100.0%
F
Friendli
$0.140
$0.400
-
-
100.0%
C
Crusoe
$0.140
$0.400
$0.140
-
100.0%
$0.140
$0.400
-
-
-
$0.140
$0.400
-
-
100.0%
$0.140
$0.400
$0.021
-
-
$0.150
$0.400
$0.060
-
100.0%
$0.200
$0.400
-
-
-
$0.300
$0.600
-
-
100.0%
M
Modal
$0.340
$0.100
$0.100
-
100.0%
$0.380
$1.150
-
-
-
$0.390
$0.970
-
-
-
$0.750
$1.000
$0.250
-
-
M
ModelRun
$0.750
$1.000
$0.200
-
100.0%
$0.900
$0.900
$0.450
-
-
Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does Gemma 4 31B Instruct perform? Vote based on your experience.

Cost vs. Quality

Compare Gemma 4 31B Instruct's benchmark performance against all models.

X-axis:
Y-axis:
Loading chart...
Other models

Try Gemma 4 31B Instruct

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Gemma 4 31B Instruct directly in your browser.

Open Playground

Frequently Asked Questions

Gemma 4 31B Instruct costs $0.000100 per 1,000 input tokens and $0.000100 per 1,000 output tokens.
Gemma 4 31B Instruct is available from 18 providers. CoreWeave offers the best price.
CoreWeave offers Gemma 4 31B Instruct at $0.100 per million input tokens, the lowest of 18 providers (input prices range from $0.100 to $0.900 per million tokens).
Yes. Over the past ~90 days, the cheapest input price for Gemma 4 31B Instruct has increased 25%, from $0.080 to $0.100 per million tokens.
We compare Gemma 4 31B Instruct with 10 similarly-priced models. See the benchmark scatter plot above to compare quality vs cost.

All Google Models

See pricing for all Google models.

View all Google models →