Llama 3.2 3B API
meta-llama/llama-3.2-3b-instruct
Call Llama 3.2 3B through UberLLM’s OpenAI-compatible API — from $0.0224/M input and $0.1474/M output, routed automatically to the cheapest healthy seller. Meta · 128,000 token context. Fee included.
Llama 3.2 3B pricing
- Input
- $0.0224
- Output
- $0.1474
- Cached input
- $0.00336
- Input
- $0.056
- Output
- $0.3685
- Cached input
- $0.00836
| Provider | Input | Output | Cached input |
|---|---|---|---|
| OpenRouter | $0.0509 | $0.335 | $0.00764 |
| Morpheus | $0.10 | $0.50 | |
| Fireworks AI | $0.15 | $0.60 | |
| Groq | $0.15 | $0.60 | |
| Together AI | $0.15 | $0.60 | |
| Venice AI | $0.15 | $0.60 | $0.0225 |
UberLLM routes every request to the cheapest healthy seller for this model. The price shown includes UberLLM’s 10% fee.
How to use Llama 3.2 3B with the OpenAI SDK
Already using the OpenAI SDK? Change one line — the base URL — and call Llama 3.2 3B with your existing code. Anthropic SDKs work against https://api.uberllm.dev/v1/messages.
from openai import OpenAI
client = OpenAI(
base_url="https://api.uberllm.dev/v1",
api_key="ull_your_key_here",
)
resp = client.chat.completions.create(
model="meta-llama/llama-3.2-3b-instruct",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)Llama 3.2 3B API — FAQ
How much does the Llama 3.2 3B API cost?
Llama 3.2 3B is listed from $0.0224 per million input tokens and $0.1474 per million output tokens through UberLLM, which routes each request to the cheapest healthy seller on a live marketplace and bills the price shown, which includes UberLLM's 10% fee.
How do I call Llama 3.2 3B via API?
Use any OpenAI-compatible SDK: set the base URL to https://api.uberllm.dev/v1, your UberLLM API key, and model "meta-llama/llama-3.2-3b-instruct". Anthropic SDKs work via https://api.uberllm.dev/v1/messages.
Is Llama 3.2 3B OpenAI-compatible on UberLLM?
Yes. Every model on UberLLM — including Llama 3.2 3B — is served through one OpenAI-compatible endpoint, so you change only the base URL and key.