Compositev12
← All models Model directory

AI model

Google: Gemma 4 26B A4B

google/gemma-4-26b-a4b-it

Google: Gemma 4 26B A4B is a 262,144-token model served on Composite at $0.0525 per million tokens in and $0.275 per million tokens out. Ranked #19 of 198 models by traffic on Composite over the last 30 days, taking 0.93% of tokens and 1% of requests (this model and its routing variants). Measured on Composite, 99.0% of its last 100 requests on Composite succeeded, the typical first token arrives in 3184 ms, output runs at about 57.0 tokens per second.

Try in Playground

Community rating

— No community ratings yet.

Sign in to rate this model. Ratings come from accounts that have run requests through Composite.

Specifications

Specifications and pricing as served by Composite
Model IDgoogle/gemma-4-26b-a4b-it
Providercv11
Context window262,144 tokens
Acceptsimage, text, video
Returnstext
Input price$0.0525 per million tokens
Output price$0.275 per million tokens
Prompt cachingSupported — cached input is billed at the provider's cache rate, on credits and plans alike
ModeratedNo
Cost on a monthly planAbout 0.6 plan credits per typical call (8k in, 1k out)
Routing endpoints10 (base plus 9 routing variants)

Traffic rank on Composite

#19 of 198

0.93% of tokens and 1% of requests over 30 days, including routing variants.

Success rate

99.0%

Across the last 100 requests Composite served for this model.

Time to first token

3184 ms

Median across the same sample.

Output speed

57.0 tok/s

Median generation rate after the first token.

Prompt cache hits

13.2%

Share of prompt tokens served from the provider's cache over 7 days.

Routing variants

The same model behind 9 alternative endpoints. Call the id directly to pin a route; the base id above picks for you.

RouteModel IDProviderPrice
Normal google/gemma-4-26b-a4b-it-normal cv11 $0.112 per million tokens input · $0.375 per million tokens output
Normal + cheapThink google/gemma-4-26b-a4b-it-normal:cheapThink cv11 $0.112 per million tokens input · $0.375 per million tokens output
Cheapest provider google/gemma-4-26b-a4b-it:cheapest-provider Darkbloom $0.0525 per million tokens input · $0.275 per million tokens output
Cheapest provider + cheapThink google/gemma-4-26b-a4b-it:cheapest-provider:cheapThink Darkbloom $0.0525 per million tokens input · $0.275 per million tokens output
cheapThink google/gemma-4-26b-a4b-it:cheapThink cv11 $0.0525 per million tokens input · $0.275 per million tokens output
Fast google/gemma-4-26b-a4b-it:fast Darkbloom $0.0525 per million tokens input · $0.275 per million tokens output
Fast + cheapThink google/gemma-4-26b-a4b-it:fast:cheapThink Darkbloom $0.0525 per million tokens input · $0.275 per million tokens output
Quality google/gemma-4-26b-a4b-it:quality NextBit $0.112 per million tokens input · $0.375 per million tokens output
Quality + cheapThink google/gemma-4-26b-a4b-it:quality:cheapThink NextBit $0.112 per million tokens input · $0.375 per million tokens output

Pricing

$0.0525 per million tokens input · $0.275 per million tokens output

Credits pay the provider’s price plus 25%; cache hits cost less.

On a monthly plan, a typical call (8k tokens in, 1k out) uses about 0.6 plan credits, at the provider's own price.

Provider

cv11

Roleplay fit

Gemini models combine large context windows with fast throughput, which keeps response times low even in busy group chats.

Context behavior

With a 262,144-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.

Cost for regular use

It is priced low enough for high-volume daily roleplay without the per-message cost adding up quickly.

From the provider

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Supplied by cv11, not written by Composite.