Traffic rank on Composite
#20 of 196
1.2% of tokens and 1.39% of requests over 30 days, including routing variants.
AI model
Google: Gemma 4 31B
google/gemma-4-31b-it
Google: Gemma 4 31B is a 262,144-token model served on Composite at $0.112 per million tokens in and $0.425 per million tokens out. Ranked #20 of 196 models by traffic on Composite over the last 30 days, taking 1.2% of tokens and 1.39% of requests (this model and its routing variants). Measured on Composite, 82.0% of its last 100 requests on Composite succeeded, the typical first token arrives in 9635 ms, output runs at about 53.5 tokens per second.
Try in PlaygroundSpecifications
| Model ID | google/gemma-4-31b-it |
|---|---|
| Provider | cv11 |
| Context window | 262,144 tokens |
| Accepts | image, text, video |
| Returns | text |
| Input price | $0.112 per million tokens |
| Output price | $0.425 per million tokens |
| 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 | About 1.1 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 10 (base plus 9 routing variants) |
Success rate
82.0%
Across the last 100 requests Composite served for this model.
Time to first token
9635 ms
Median across the same sample.
Output speed
53.5 tok/s
Median generation rate after the first token.
Prompt cache hits
1.7%
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.
| Route | Model ID | Provider | Price |
|---|---|---|---|
| Normal | google/gemma-4-31b-it-normal |
cv11 | $0.112 per million tokens input · $0.425 per million tokens output |
| Normal + cheapThink | google/gemma-4-31b-it-normal:cheapThink |
cv11 | $0.112 per million tokens input · $0.425 per million tokens output |
| Cheapest provider | google/gemma-4-31b-it:cheapest-provider |
DeepInfra | $0.112 per million tokens input · $0.425 per million tokens output |
| Cheapest provider + cheapThink | google/gemma-4-31b-it:cheapest-provider:cheapThink |
DeepInfra | $0.112 per million tokens input · $0.425 per million tokens output |
| cheapThink | google/gemma-4-31b-it:cheapThink |
cv11 | $0.112 per million tokens input · $0.425 per million tokens output |
| Fast | google/gemma-4-31b-it:fast |
DeepInfra | $0.112 per million tokens input · $0.425 per million tokens output |
| Fast + cheapThink | google/gemma-4-31b-it:fast:cheapThink |
DeepInfra | $0.112 per million tokens input · $0.425 per million tokens output |
| Quality | google/gemma-4-31b-it:quality |
Crusoe | $0.175 per million tokens input · $0.500 per million tokens output |
| Quality + cheapThink | google/gemma-4-31b-it:quality:cheapThink |
Crusoe | $0.175 per million tokens input · $0.500 per million tokens output |
Pricing
$0.112 per million tokens input · $0.425 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 1.1 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 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Supplied by cv11, not written by Composite.
Related models
Composite Gemini Router · Google: Gemini 3.8 Flash (Drafted) · Google: Gemini 3.7 Flash (Drafted)