GoogleOpen weightsReleased Apr 2, 2026

Gemma 4 26B A4B pricing, benchmarks and cost analysis

Compare Google guide

Intelligence#64 / 66

141.9

Epoch Capabilities Index (ECI)range 138.9 to 143.4

Speed

No speed data

Throughput not measured for this model

Cost#6 / 101

$89.40 / mo

In $0.090Out $0.300 per 1MCache discount 44%

Context#79 / 101

262K

Context window, tokens

Ranks are among the 101 models we track (intelligence = Epoch Capabilities Index by Epoch AI, CC BY 4.0; intelligence and speed: among those with data; cost: #1 is cheapest). Monthly cost uses the default workload of 2,000 input and 500 output tokens, 10,000 requests a day, 40% cached.

Comparison summary

On the default workload (2,000 input and 500 output tokens, 10,000 requests a day, 40% cached), Gemma 4 26B A4B comes to $89.40 a month, 90% below the $873 median of the 101 models we track. It ranks #6 of 101 on cost, where #1 is the cheapest.

It scores 141.9 on the Epoch Capabilities Index (#64 of 66). Among the 5 other models within 2 points, none costs less, and it costs 58% less than their median ($212). The cheapest stable-priced model that scores at least as high is Qwen3.7 Flash (144.1) at $31.74 a month, 64% less.

Cached input is 44% cheaper than fresh input, a smaller discount than the 90% median. The weights are open, so other hosts can serve it and prices may differ from the provider's own. Its listed price changed on five or more days in the last month, usually because the cheapest host changed, so check the provider before relying on the figures above.

Technical specifications

Context window: 262K tokens
Input price: $0.090 / 1M
Cached input price: $0.050 / 1M
Output price: $0.300 / 1M
Cache discount: 44%
Batch API: Not listed
Open weights: Yes
Release date: Apr 2, 2026
Price volatility: Volatile (5+ changes in 30 days)

Benchmarks

Best score for this model on each leaderboard, ranked against the other models listed there.

Your monthly bill

Standard

$89.40 / month

Input: $32.40
Cached input: $12.00
Output: $45.00

Batch

No batch rates are listed for this model.

Price history

Oct 19, 2026Input $0.068 â†’ $0.090â–² 32%
Oct 19, 2026Output $0.225 â†’ $0.300â–² 33%
Oct 19, 2026Cached input $0.037 â†’ $0.050â–² 35%
Oct 17, 2026Input $0.090 â†’ $0.068â–¼ 24%
Oct 17, 2026Output $0.300 â†’ $0.225â–¼ 25%
Oct 17, 2026Cached input $0.050 â†’ $0.037â–¼ 26%
Oct 12, 2026Input $0.068 â†’ $0.090â–² 32%
Oct 12, 2026Output $0.225 â†’ $0.300â–² 33%
Oct 12, 2026Cached input $0.037 â†’ $0.050â–² 35%
Oct 10, 2026Input $0.090 â†’ $0.068â–¼ 24%
Oct 10, 2026Output $0.300 â†’ $0.225â–¼ 25%
Oct 10, 2026Cached input $0.050 â†’ $0.037â–¼ 26%
Oct 5, 2026Input $0.068 â†’ $0.090â–² 32%
Oct 5, 2026Output $0.225 â†’ $0.300â–² 33%
Oct 5, 2026Cached input $0.037 â†’ $0.050â–² 35%
Oct 3, 2026Input $0.090 â†’ $0.068â–¼ 24%
Oct 3, 2026Output $0.300 â†’ $0.225â–¼ 25%
Oct 3, 2026Cached input $0.050 â†’ $0.037â–¼ 26%
Sep 28, 2026Input $0.068 â†’ $0.090â–² 32%
Sep 28, 2026Output $0.225 â†’ $0.300â–² 33%
Sep 28, 2026Cached input $0.037 â†’ $0.050â–² 35%
Sep 26, 2026Input $0.090 â†’ $0.068â–¼ 24%
Sep 26, 2026Output $0.300 â†’ $0.225â–¼ 25%
Sep 26, 2026Cached input $0.050 â†’ $0.037â–¼ 26%
Sep 13, 2026Input $0.042 â†’ $0.090â–² 114%
Sep 13, 2026Output $0.220 â†’ $0.300â–² 36%
Sep 13, 2026Cached input $0.004 â†’ $0.050â–² 1150%
Sep 11, 2026Input $0.070 â†’ $0.042â–¼ 40%
Sep 11, 2026Output $0.340 â†’ $0.220â–¼ 35%
Sep 11, 2026Cached input $0.007 â†’ $0.004â–¼ 43%

Cheaper alternatives

Models with stable pricing and a Epoch Capabilities Index within 2 points of Gemma 4 26B A4B (or higher) that cost less for the default workload.

Qwen3.7 Flash64% cheaper$31.74 a monthECI 144.1

Compare these