AI model
meta-llama/llama-3.3-70b-instruct
Meta: Llama 3.3 70B Instruct is a 131,072-token model served on Composite at $0.125 per million tokens in and $0.400 per million tokens out. Ranked #166 of 179 models by traffic on Composite over the last 30 days, taking 0% of tokens and 0% of requests.
Try in Playground| Model ID | meta-llama/llama-3.3-70b-instruct |
|---|---|
| Provider | cv11 |
| Context window | 131,072 tokens |
| Accepts | text |
| Returns | text |
| Input price | $0.125 per million tokens |
| Output price | $0.400 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) |
Make a Composite API key and type meta-llama/llama-3.3-70b-instruct as the model name. JanitorAI takes the full URL https://composite.lucidity.sh/v1/chat/completions; SillyTavern, ChubAI, Agnai and RisuAI take https://composite.lucidity.sh/v1. It runs on credits, a plan, or your own provider key.
JanitorAI setup · SillyTavern setup · Best Janitor AI proxies compared
#166 of 179
0% of tokens and 0% of requests over 30 days.
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 | meta-llama/llama-3.3-70b-instruct-normal |
cv11 | $0.887 per million tokens input · $0.887 per million tokens output |
| Normal + cheapThink | meta-llama/llama-3.3-70b-instruct-normal:cheapThink |
cv11 | $0.887 per million tokens input · $0.887 per million tokens output |
| Cheapest provider | meta-llama/llama-3.3-70b-instruct:cheapest-provider |
DeepInfra | $0.125 per million tokens input · $0.400 per million tokens output |
| Cheapest provider + cheapThink | meta-llama/llama-3.3-70b-instruct:cheapest-provider:cheapThink |
DeepInfra | $0.125 per million tokens input · $0.400 per million tokens output |
| cheapThink | meta-llama/llama-3.3-70b-instruct:cheapThink |
cv11 | $0.125 per million tokens input · $0.400 per million tokens output |
| Fast | meta-llama/llama-3.3-70b-instruct:fast |
DeepInfra | $0.125 per million tokens input · $0.400 per million tokens output |
| Fast + cheapThink | meta-llama/llama-3.3-70b-instruct:fast:cheapThink |
DeepInfra | $0.125 per million tokens input · $0.400 per million tokens output |
| Quality | meta-llama/llama-3.3-70b-instruct:quality |
CoreWeave | $0.887 per million tokens input · $0.887 per million tokens output |
| Quality + cheapThink | meta-llama/llama-3.3-70b-instruct:quality:cheapThink |
CoreWeave | $0.887 per million tokens input · $0.887 per million tokens output |
$0.125 per million tokens input · $0.400 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.
cv11
Llama models are a widely-supported open baseline, useful when you want predictable, well-documented behavior.
With a 131,072-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.
It is priced low enough for high-volume daily roleplay without the per-message cost adding up quickly.
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...
Supplied by cv11, not written by Composite.
Meta: Muse Ember · Meta: Muse Spark Open · Meta: Muse Wonder