Traffic rank on Composite
#137 of 197
0% of tokens and 0.01% of requests over 30 days.
AI model
Google: Gemma 4 26B A4B (Free)
google/gemma-4-26b-a4b-it:free
Google: Gemma 4 26B A4B (Free) is a 262,144-token model free on Composite. Ranked #137 of 197 models by traffic on Composite over the last 30 days, taking 0% of tokens and 0.01% of requests. Measured on Composite, 100.0% of its last 18 requests on Composite succeeded, the typical first token arrives in 1320 ms, output runs at about 42.4 tokens per second.
Try in PlaygroundSpecifications
| Model ID | google/gemma-4-26b-a4b-it:free |
|---|---|
| Provider | cv11 |
| Context window | 262,144 tokens |
| Accepts | image, text, video |
| Returns | text |
| Input price | Included in free allowance |
| Output price | Included in free allowance |
| Prompt caching | Supported — cached input is billed at the provider's cache rate, on credits and plans alike |
| Moderated | No |
| Cost on a monthly plan | Free - does not spend plan credits |
| Routing endpoints | 1 |
Success rate
100.0%
Across the last 18 requests Composite served for this model.
Time to first token
1320 ms
Median across the same sample.
Output speed
42.4 tok/s
Median generation rate after the first token.
Pricing
Free - 80 requests/day shared across free models; each call counts as 2
Credits pay the provider’s price plus 25%; cache hits cost less.
Monthly plans serve this model without spending any of their included credits.
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 free on Composite, which makes it a reasonable place to test a character card, preset or lorebook before connecting your own provider.
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.
Related models
Composite Gemini Router · Google: Gemini 3.8 Flash (Drafted) · Google: Gemini 3.7 Flash (Drafted)