Gemma 4 26B A4B IT

gemma-4-26b-a4b-it by Google Cloud Released April 4, 2026
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off
Input from
$0 / 1M
Output from
$0 / 1M
Cached input from
$0.009 / 1M
Context window
262K
Endpoints
8
from 6 providers
Regions
Global, Europe, United States

About Gemma 4 26B A4B IT

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.

Gemma 4 26B A4B IT is a chat model by Google Cloud, available on Eden AI through 8 endpoints from 6 providers, including a free endpoint (paid endpoints from $0.06 per million input tokens), with a context window of up to 262K tokens.

Providers and prices

8 endpoints from 6 providers, cheapest first, in USD per million tokens. Every one is called with the same Eden AI key: pin one with its endpoint ID, or let Eden AI route for you. .

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
Google CloudOfficial−%google/gemma-4-26b-a4b-it
Global
262K
$0$0
$0
$
ReasoningToolsJSONCacheVisionWeb
FlexAIOfficial−%flexai/gemma-4-26B-A4B-it
Global
262K
$0.06$0.06
$0.33
$0.009
ReasoningToolsJSONCacheVisionWeb
DeepInfra (United States)Official−%deepinfra/google/gemma-4-26B-A4B-it
United States
262K
$0.07$0.07
$0.34
$
ReasoningToolsJSONCacheVisionWeb
Cloudflare (CF/GOOGLE/GEMMA-4-26B-A4B-IT)Official−%cloudflare/@cf/google/gemma-4-26b-a4b-it
CF/GOOGLE/GEMMA-4-26B-A4B-IT
256K
$0.1$0.1
$0.3
$0.05
ReasoningToolsJSONCacheVisionWeb
Google CloudOfficial−%vertex/google/gemma-4-26b-a4b-it-maas
Global
262K
$0.15$0.15
$0.6
$0.015
ReasoningToolsJSONCacheVisionWeb
Google Cloud (Europe)Official−%vertex/google/gemma-4-26b-a4b-it-maas@eu
Europe
262K
$0.165$0.165
$0.66
$0.0165
ReasoningToolsJSONCacheVisionWeb
Google Cloud (United States)Official−%vertex/google/gemma-4-26b-a4b-it-maas@us
United States
262K
$0.165$0.165
$0.66
$0.0165
ReasoningToolsJSONCacheVisionWeb
Scaleway (Europe)Official−%scaleway/gemma-4-26b-a4b-it
Europe
256K
$0.2802$0.2802
$0.5603
$
ReasoningToolsJSONCacheVisionWeb

Performance

Measured on real Eden AI traffic over the last 30 days. Endpoints with too little traffic are not shown.

Fastest first token
0.39 s
Scaleway (Europe)
Lowest latency
1.25 s
Google Cloud (Europe)
Highest throughput
127.19 tok/s
Scaleway (Europe)
Best availability
100%
FlexAI
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Google Cloud
0.9 s
22.27 s
45.53 s
45.79 tok/s
95.09%
7.08%
25.15%
52.85%
FlexAI
0.76 s
1.47 s
6.37 s
48.6 tok/s
100%
72.6%
0%
0%
DeepInfra (United States)
0.64 s
6.78 s
28.45 s
29.76 tok/s
100%
0%
0%
0%
Cloudflare (CF/GOOGLE/GEMMA-4-26B-A4B-IT)
s
s
s
tok/s
%
%
%
%
Google Cloud
10.24 s
1.25 s
4.65 s
34.69 tok/s
99.83%
23.71%
7.84%
19.44%
Google Cloud (Europe)
11.28 s
1.25 s
4.24 s
34.73 tok/s
99.83%
24.45%
7.41%
2.22%
Google Cloud (United States)
s
s
s
tok/s
%
%
%
%
Scaleway (Europe)
0.39 s
5.67 s
35.09 s
127.19 tok/s
98.57%
0%
4.51%
4.42%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call Gemma 4 26B A4B IT with Eden AI

Use the model ID to let Eden AI pick an endpoint, or an endpoint ID from the table above to pin one.

import requests

response = requests.post(
    "https://api.edenai.run/v3/chat/completions",
    headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
    json={
        "model": "",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about Gemma 4 26B A4B IT

On Eden AI, prices for this model start at $0 per million input tokens and $0 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

Up to 262K tokens, depending on the endpoint.

8 endpoints from 6 providers, available in: Global, Europe, United States. All of them are called with the same Eden AI API key.

Yes. At least one endpoint is hosted in Europe; pin it with its endpoint ID from the providers table to keep requests in the EU.

Over the last 30 days, the fastest first token was 0.39 s (Scaleway (Europe)) and the highest throughput was 127.19 tokens per second (Scaleway (Europe)).