AI Token Price
Google

Google · 2 current models

Gemma API pricing

Estimate your costCompare with Ministral 3 3B

Google's open-weight models. Gemma 4 comes as a 31B dense model and a 26B mixture-of-experts model with 3.8B active parameters.

Gemma 4 26B-A4B

▼ 2% on 13 Oct
Input
$0.042
per 1M tokens
Output
$0.22
per 1M tokens
Cached input
—
not published
Batch
—
no discount offered
Context window
256K
tokens
OpenRouter listing Repriced on 13 Oct 2026: input down 38%, output down 2% (was $0.0675 / $0.225)

Capability score 142, 27th of 29 current models scored on the Epoch Capabilities Index (range 139–144).
GPT-6 Luna scores higher (157) and costs 44% less on a coding agent: $25.98 vs $46.10 a month.

Compare the two →

Source: Epoch Capabilities Index by Epoch AI, CC BY 4.0, read 11 Nov 2026. What the score means

What it costs in practice

Gemma 4 26B-A4B at list prices, no batch discount.

1,000 chat replies1,500 tokens in and 300 out each$0.13
Summarising 100 long reports20,000 tokens in and 800 out each$0.10
A month of a coding agent400 tasks, 85% of input cached$33.26

The coding-agent example assumes 85% of input is served from cache, typical for agents that resend the same context each step. Work out AI agent cost on Gemma 4 26B-A4B

Details

API model IDgemma-4-26b-a4b-it
Released3 Apr 2026
WeightsOpen, 25.2B total and 3.8B active parameters
Capability score142 (range 139–144, from 5 benchmarks; Epoch Capabilities Index)
StatusCurrent

Cheapest host listed on OpenRouter (Darkbloom). DeepInfra charges $0.07 / $0.34.

Checked 13 Oct 2026 against OpenRouter listing .

Estimate your monthly cost

List prices, no batch discount

ModelInput / output per 1MPer month
Gemma 4 26B-A4B$0.042 / $0.22$0.86
Gemma 4 31B$0.090 / $0.34$1.58
Ministral 3 3BSimilar price · Mistral AI$0.10 / $0.10$1.20

Type amounts like 500K, 25M or 2B.

Price Gemma 4 26B-A4B in: Token cost calculator · AI agent cost · Token counter

Cheapest in its class

No current general-purpose small and fast model from another family costs meaningfully less than Gemma 4 26B-A4B.

Similar price from another provider: Ministral 3 3B, $0.10 / $0.10. Compare

Compare Gemma 4 26B-A4B with

Side by side: prices, cached and batch rates, and the cost of the same workload.

Other Gemma models

Prices are the cheapest listed on OpenRouter; hosts vary.

Model Input / 1M Output / 1M Cached input Context Released
Gemma 4 31B
Open weights · via OpenRouter · Source
 $0.090 $0.34 — 256K 2 Apr 2026

Gemma 4 31B details

Gemma 4 31B

$0.090 / $0.34 per 1M tokens256K context

Released 2 Apr 2026 · gemma-4-31b-it

Cheapest host listed on OpenRouter (DeepInfra).

Checked 13 Oct 2026 against OpenRouter listing .

Compare Gemma 4 26B-A4B

No ready-made comparisons for this family yet.

Compare with up to three other models

Price history

All changes
  • OpenAI
    The cheapest OpenRouter hosts repriced 6 open-weight models, mostly downwards, including gpt-oss-120b (now $0.03 / $0.15) and Qwen3.8 27B (now $0.039 / $1.25). Source

Every dated price: price records · CSV. Cite as: AI Token Price, Gemma pricing, https://aitokenprice.com/pricing/gemma#price-history

Google pricing rules

  • Batch requests cost 50% less.
  • Gemini 3.1 Pro charges a higher rate for prompts above 200K tokens.
  • Gemini 3.8 Flash is on a promotional price until 31 December 2026.

Gemini API pricing, free tier and billing

Questions

How much does Gemma 4 26B-A4B cost?

As of 13 Oct 2026, Gemma 4 26B-A4B costs $0.042 per million input tokens and $0.22 per million output tokens. Prices checked 13 Oct 2026.

What is Gemma 4 26B-A4B's context window?

256K tokens.