Measured on Composite
This model has not carried enough traffic on Composite yet to publish a success rate, a latency figure or a traffic rank. The numbers appear here once it has.
AI model
Meta: Llama 4 Scout
meta-llama/llama-4-scout
Meta: Llama 4 Scout is a 327,680-token model served on Composite at $0.100 per million tokens in and $0.300 per million tokens out.
Try in PlaygroundSpecifications
| Model ID | meta-llama/llama-4-scout |
|---|---|
| Provider | DeepInfra |
| Context window | 327,680 tokens |
| Accepts | text, image |
| Returns | text |
| Input price | $0.100 per million tokens |
| Output price | $0.300 per million tokens |
| Prompt caching | Not offered for this model |
| Moderated | No |
| Cost on a monthly plan | About 0.9 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 2 (base plus 1 routing variant) |
Routing variants
The same model behind 1 alternative endpoint. Call the id directly to pin a route; the base id above picks for you.
| Route | Model ID | Provider | Price |
|---|---|---|---|
| cheapThink | meta-llama/llama-4-scout:cheapThink |
DeepInfra | $0.100 per million tokens input · $0.300 per million tokens output |
Pricing
$0.100 per million tokens input · $0.300 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 0.9 plan credits, at the provider's own price.
Provider
DeepInfra
Roleplay fit
Llama models are a widely-supported open baseline, useful when you want predictable, well-documented behavior.
Context behavior
With a 327,680-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
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
Supplied by DeepInfra, not written by Composite.
Related models
Meta: Muse Spark Open · Meta: Muse Wonder · Meta: Muse Spark 1.3 Contributor