Skip to content
English

Switch theme

// Google

Gemma 4 26B A4B

A Google model. 4 prices across 4 channels side by side, each with its source and check date – plus specs, licence, speed and benchmarks.

Official in/out per 1M
—
Lowest (DeepInfra)
$0.07 / $0.34
Context
262K
AA index
16.7

Prices checked 2026-10-22Official sources linked on every rowNo estimates

01Specs at a glance

Official values first; gaps filled from OpenRouter’s API where the vendor page is silent.

VendorGoogle
Context window262K (262,144 tokens)
Max output16K
InputImage · Text · Video
OutputText
Tool calling / JSONYes / Yes
Weights & licenceOpen weights · Apache-2.0 · Hugging Face
Parameters25.8B (from weight files)
ReleasedApr 3, 2026
Model IDsgoogle/gemma-4-26b-a4b-it

02Prices on 4 channels

Per 1M tokens, in the currency each source publishes (1 USD = 6.7 CNY for the blended column). Sorted: official first, then cheapest.

ChannelSourceInputOutputCache hitBlended $ContextNotes
DeepInfra · fp8
Via OpenRouter / provider listed there
OpenRouter 10-22 $0.07 $0.34 — 0.138 262K DeepInfra price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against DeepInfra's own page
Parasail · bf16
Via OpenRouter / provider listed there
OpenRouter 10-22 $0.13 $0.4 $0.05 0.198 262K Parasail price as listed on OpenRouter (pass-through; quantization=bf16; discount field=0); not checked against Parasail's own page
Novita · bf16
Via OpenRouter / provider listed there
OpenRouter 10-22 $0.13 $0.4 — 0.198 262K Novita price as listed on OpenRouter (pass-through; quantization=bf16; discount field=0); not checked against Novita's own page
SiliconFlow · fp8
Via OpenRouter / provider listed there
OpenRouter 10-22 $0.14 $0.4 $0.05 0.205 262K SiliconFlow price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against SiliconFlow's own page

“Official” = vendor pricing page; “Platform” = the platform’s own pricing page; “OpenRouter” = price listed on OpenRouter, not checked on the platform’s site. Click a source tag to open the original page.

03Where you can use it

Derived only from the price sources above. Country restrictions are set by each vendor – check their terms before you sign up.

04Performance

All results →

Speed and AA index from Artificial Analysis public leaderboards (not our own tests); benchmark scores from our benchmark library, best result per benchmark.

AA indexGemma 4 26B A4B (Reasoning)
16.7
Output speed (median)
64 tok/s
Time to first token
1.03s
AA index per $ (blended)
121.25
BenchmarkBest scoreSourceDate
LMArena Text1438official2026-10-08
LMArena WebDev1359official2026-10-08
LMArena Vision1242official2026-10-02
GPQA Diamond73.2%independent2026-08-06
AIME (OTIS Mock AIME 2024–2025)82.2%independent2026-08-28

05Price changes we recorded

All price changes →

From our daily re-checks of the sources above.

No price change recorded since we started tracking (2026-10-10).

06More from Google

FAQ

How much does the Gemma 4 26B A4B API cost?

There is no official pay-as-you-go price in our data. The lowest listed price is $0.07 / $0.34 on DeepInfra.

What is the context window of Gemma 4 26B A4B?

262K tokens of context, up to 16K output tokens. Platforms may cap it lower – see the table.

Is Gemma 4 26B A4B open source?

Yes, the weights are published on Hugging Face (google/gemma-4-26B-A4B-it). Licence: Apache-2.0.

Data updated: Model API prices · HF model metadata(UTC+8)