Back to models

Gemma 4 26B A4B

Cloudflare•
Modalities
Input / Output Price
$0.10/$0.30/ 1M
Context Length
256K tokens
Parameters
-

Providers

Different companies host the same model. DOS.AI routes your request to one of them based on the routing mode you pick - Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).

Reasoning effortⓘAll
ProviderInput /1MOutput /1M
Latency
ThroughputUptime
Cloudflare
$0.10$0.30---

Pricing

Rates from the DOS.AI catalog for the billing units shown. Caching and provider discounts mean the price actually paid is often below the listed one.

Weighted Averagei
Weighted Avg Input Price
$0.10/ 1M tokens
Equal to list price
Weighted Avg Output Price
$0.30/ 1M tokens
Equal to list price
Price History1 verified endpoints
Weighted Average($0.10)
$0.00$0.04$0.08$0.1230d ago24d ago18d ago12d ago6d agoToday
Provider↕
Effective in /M↕
Effective out /M↕
Cache read /M↕
Latency↕
Throughput↕
Uptime↕
Savings↕
Cloudflare
$0.10
$0.30-----
Based on settled billing for the last 30d.Effective pricing represents the average price paid for requests to this endpoint, factoring in caching, discounts, and tiered pricing. Listed pricing shows the posted provider list prices.

Observed reliability

Success rate across observed provider requests. This is historical sample data, not live health or an uptime guarantee.

Not enough observations

Last 7 days

There are not enough valid request observations to report a success rate.

Benchmarks

Dated third-party measurements with source links.

Artificial Analysis

Overall · Snapshot captured:

Artificial Analysis Intelligence Index
16.7
Coding Index
39.3
Agentic Index
2.9

API Integration

Use the DOS API to integrate Gemma 4 26B A4B into your applications. Compatible with standard OpenAI SDKs for easy drop-in migration.

</>Run inference
curl https://api.dos.ai/v1/chat/completions \
  -H "Authorization: Bearer $DOS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma-4-26b-a4b-it",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }'